CN112579751A - User information filling method and device and computer equipment - Google Patents
User information filling method and device and computer equipment Download PDFInfo
- Publication number
- CN112579751A CN112579751A CN202011454835.6A CN202011454835A CN112579751A CN 112579751 A CN112579751 A CN 112579751A CN 202011454835 A CN202011454835 A CN 202011454835A CN 112579751 A CN112579751 A CN 112579751A
- Authority
- CN
- China
- Prior art keywords
- user information
- information
- user
- target
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012216 screening Methods 0.000 claims abstract description 22
- 239000013598 vector Substances 0.000 claims description 68
- 238000012545 processing Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001502 supplementing effect Effects 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
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- 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
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Acoustics & Sound (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a user information filling method, a device and computer equipment, wherein the method comprises the following steps: screening out a target service model according to personal information of a user so as to carry out conversation on the user; and analyzing the content of the conversation through the target service model, and filling user information into a business form according to a preset format. The invention has the beneficial effects that: the method comprises the steps of selecting a proper service model to carry out conversation for a user according to personal information of the user, obtaining user information keywords from the conversation according to the corresponding service model, enabling the user information keywords to be obtained more reasonably, obtaining corresponding target candidate user information according to the user information keywords, converting the target candidate user information into a preset format, and filling the target candidate user information into a business form, so that the user information is correctly and quickly filled into the business form.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a user information filling method and device and computer equipment.
Background
In some special scenes, a certain format requirement is needed when a user fills in user information, and because the user information expressed by the user often cannot meet the format requirement in the AI video call process, and the automatic filling in of the user information in a session is difficult to realize by the existing character extraction technology, in the prior art, the user generally performs handwriting, and the handwriting delays the user filling time, the user often abandons the service under the condition that the user is not matched or has no patience. Therefore, a method for automatically filling in user information is needed.
Disclosure of Invention
The invention mainly aims to provide a user information filling method, a user information filling device and computer equipment, and aims to solve the problem that standard user information cannot be automatically filled according to conversation contents in the prior art.
The invention provides a user information filling method, which comprises the following steps:
acquiring parameter information of various service models according to personal information of a user;
inputting the parameter information into the corresponding service models to obtain temporary service models corresponding to the service models respectively;
acquiring question information input by the user;
screening out a target service model from the temporary service models according to the problem information so as to carry out conversation on the user;
analyzing the content of the conversation through the target service model to obtain corresponding user information keywords;
inquiring a plurality of candidate user information according to the user information key words so as to be selected by the user;
receiving target candidate user information selected by a user from the candidate user information;
and filling the target candidate user information into a service form according to a preset format.
Further, the step of analyzing the content of the dialog through the target service model to obtain a corresponding user information keyword includes:
in the target service model, performing voice-to-word processing on the content of the conversation to obtain preliminary text information corresponding to the content of the conversation;
standardizing the preliminary text information to obtain target text information;
performing word segmentation on the target text information, and performing vectorization processing on each word after word segmentation according to a text sequence to obtain a target text vector corresponding to the target text information;
and extracting the user information keywords in the target text vector according to a preset user information extraction method.
Further, the step of extracting the user information keyword in the target text vector according to a preset user information extraction method includes:
inputting the target text vector into a word segmentation device to obtain a plurality of corresponding word vectors;
deleting irrelevant words in the word vectors according to the parts of speech of the word vectors to obtain a plurality of corresponding target word vectors;
according to the formula
Calculating the correlation value of each target word vector and other target word vectors; wherein R (x)i) Representing the correlation value corresponding to the ith target word vector, d is a preset parameter, and xiDenotes the ith target word vector, xjRepresenting the jth target word vector, n representing the number of the target word vectors;
and obtaining the user information keywords from the target word vector according to the correlation value.
Further, the step of screening out a target service model from the temporary service models according to the question information includes:
calculating the similarity between the problem information and each temporary service model through a preset similarity calculation formula;
and screening the target service model from the temporary service models according to the calculated similarity to carry out conversation on the user.
Further, the step of querying a plurality of candidate user information according to the user information keyword for selection by the user includes:
detecting a historical living address library of the user according to the user information key words, and detecting in a preset address library according to the key words; the user information keywords are address keywords;
and screening a plurality of candidate addresses according to the detection result for the user to select.
Further, the step of filling the target candidate user information into a service form according to a preset format includes:
detecting whether the target candidate user information in the business table is matched with a national standard five-level base table;
if not, acquiring corresponding standard user information in a corresponding user information database according to the target candidate user information;
and filling the standard user information into the service form.
The invention also provides a user information filling device, which comprises:
the parameter information acquisition module is used for acquiring parameter information of various service models according to personal information of a user;
the parameter information input module is used for inputting the parameter information into the corresponding service models to obtain temporary service models corresponding to the service models respectively;
the problem information acquisition module is used for acquiring the problem information input by the user;
the screening module is used for screening a target service model from the temporary service models according to the problem information so as to carry out conversation on the user;
the analysis module is used for analyzing the content of the conversation through the target service model to obtain a corresponding user information keyword;
the query module is used for querying a plurality of candidate user information according to the user information key words so as to be selected by the user;
the receiving module is used for receiving target candidate user information selected by a user from the candidate user information;
and the filling module is used for filling the target candidate user information into a service form according to a preset format.
Further, the parsing module includes:
the input submodule is used for carrying out voice-to-word processing on the content of the conversation in the target service model to obtain preliminary text information corresponding to the content of the conversation;
the standardization processing submodule is used for carrying out standardization processing on the preliminary text information to obtain target text information;
the word segmentation sub-module is used for segmenting the target text information and vectorizing each segmented word according to the text sequence to obtain a target text vector corresponding to the target text information;
and the user information keyword acquisition submodule is used for extracting the user information keywords in the target text vector according to a preset user information extraction method.
The invention also provides a computer device comprising a memory storing a computer program and a processor implementing the steps of any of the above methods when the processor executes the computer program.
The invention also provides a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method of any of the above.
The invention has the beneficial effects that: the method comprises the steps of selecting a proper service model to carry out conversation for a user according to personal information of the user, obtaining user information keywords from the conversation according to the corresponding service model, enabling the user information keywords to be obtained more reasonably, obtaining corresponding target candidate user information according to the user information keywords, converting the target candidate user information into a preset format, and filling the target candidate user information into a business form, so that the user information is correctly and quickly filled into the business form.
Drawings
Fig. 1 is a flowchart illustrating a user information filling method according to an embodiment of the present invention;
fig. 2 is a schematic block diagram illustrating a structure of a user information filling apparatus based on an AI video call according to an embodiment of the present invention;
fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
It should be noted that all directional indicators (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship between the components, the motion situation, etc. in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indicator is changed accordingly, and the connection may be a direct connection or an indirect connection.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.
In addition, the descriptions related to "first", "second", etc. in the present invention are only for descriptive purposes and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a method for filling user information, including:
s1: acquiring parameter information of various service models according to personal information of a user;
s2: inputting the parameter information into the corresponding service models to obtain temporary service models corresponding to the service models respectively;
s3: acquiring question information input by the user;
s4: screening out a target service model from the temporary service models according to the problem information so as to carry out conversation on the user;
s5: analyzing the content of the conversation through the target service model to obtain corresponding user information keywords;
s6: inquiring a plurality of candidate user information according to the user information key words so as to be selected by the user;
s7: receiving target candidate user information selected by a user from the candidate user information;
s8: and filling the target candidate user information into a service form according to a preset format.
As described in the above step S1, parameter information of various service models is obtained according to the personal information of the user. Wherein, the personal information of the user can be obtained according to the registration information of the user in the App corresponding to the AI video call, if the personal information in the registration information is imperfect, the perfect personal information can be obtained in the user database of the company according to the registration information, the personal information can include one or more information such as loan amount, home address, company user information, annual income and the like corresponding to the user, then the grade information of the user is obtained according to the information, taking the loan amount as an example, the grade information of the user can be obtained according to the corresponding relationship preset by the loan amount and the grade information of the user, then the parameter information of each service model is obtained according to the grade information of the user, namely, the corresponding service can be provided for the user according to the grade of the user, so that the answer of the question answered by the corresponding service model can better meet the needs of the user, therefore, the communication is smoother, and the communication is more smooth, so that the inquiry and the acquisition of the geographic position of the user are facilitated. The user information can be address information, contact information, medical record information and the like. The parameter information may be parameter values in different functions, and it should be understood that if the parameter values are parameter values, corresponding relationships between different users and the parameter values are established in advance, so that the effect of AI communication between the corresponding service model and the users is better. The establishing of the corresponding relationship between the user and the parameter value may specifically be dividing each user into different grades according to the information of the user, taking the user of the same grade as the training data of the grade, inputting the training data to each service model for training to obtain the parameter of each service model, establishing the corresponding relationship between the grade and the corresponding parameter value based on each grade, and subsequently obtaining the corresponding parameter value only by obtaining the grade of the user. For example, if the level of the user is detected to be a first-level user, the parameter value corresponding to the first-level user is input into the corresponding service model, and the first-level user is served through the service model with the parameter value corresponding to the first-level user.
As described in step S2, the parameter information is input into the corresponding service model to obtain the temporary service model corresponding to each service model, and the service models adopted for AI video call are different according to different chat contents of the user, and the service models may include a business problem model, a special requirement model, a high risk model, a consultation model, and a chatting model. Because different users have different conditions and different requirements, the corresponding parameter information is input into the corresponding service model, so that the effect of the user in the AI video call is better.
As described in the above step S3, the question information input by the user is acquired. The obtaining mode can be that a microphone collects the dialogue information of the user, the dialogue information is converted into character information through a voice-to-character technology, and the problem information of the user is obtained through a semantic recognition technology.
As described in step S4, the temporary service model is filtered according to the question information to perform a dialog for the user. The screening method comprises the steps of calculating the similarity between the problem information and each temporary service model through a similarity calculation formula, calculating the similarity through cosine similarity by using the similarity calculation formula, namely vectorizing the problem information to obtain first vectors, wherein each temporary service model corresponds to a second vector, and then calculating the similarity according to the formula
The similarity is calculated, wherein,
in order to be the degree of similarity,
a first vector is represented by a first vector,
a second vector is represented that represents the second vector,
representing the ith dimension of the first vector,
representing the ith dimension of the second vector. And screening out the temporary service models according to the calculated similarity, wherein the screening rule can be that the temporary service model with the highest similarity is selected to carry out conversation on the user.
As described in step S5, the content of the dialog is analyzed by the target service model to obtain the corresponding user information keyword. Namely, each service model has an NLP (natural language processing) module. It should be understood that, as the content of the conversation in each service model is different, the positions of the user information keywords appearing in the service models are also different, so the NLP module in each service model is preferably trained based on the corresponding content of the conversation in each service model and the user information keywords contained in the content of the conversation. And obtaining the corresponding user information key words.
As described in step S6, since the user may refer to a plurality of user information candidates and may also provide some fuzzy user information during the conversation process, the user may search a plurality of user information candidates in a preset user information database according to the user information keyword for the user to select, where the preset user information database may be one or more of a company database, a user information database, and a professional knowledge database. And then providing a plurality of candidate user information to the user according to the logic of the screening.
As described in the above step S7, target candidate user information selected by the user from the candidate user information is received. The method for selecting the candidate user information by the user is not limited, for example, screen clicking, keyboard control, remote selection and the like can be performed, so that the corresponding receiving method is not limited, and the target candidate user information selected by the user can be received.
As described in the above step S8, the target candidate user information is filled into the service form according to the preset format. The selected target candidate user information is not necessary to serve the writing form of the business form, so that the corresponding format, namely the preset format, can be found in the standard database according to the selected target candidate user information, and then the business form is filled according to the preset format, so that automatic filling is realized, the application timeliness of the user is improved, the occupation of user flow, time and the like is reduced, the timeliness from application to payment is improved, and the satisfaction degree of the user is improved.
In one embodiment, the step S5 of parsing the content of the dialog through the target service model to obtain a corresponding user information keyword includes:
s501: in the target service model, performing voice-to-word processing on the content of the conversation to obtain preliminary text information corresponding to the content of the conversation;
s502: standardizing the preliminary text information to obtain target text information;
s503: performing word segmentation on the target text information, and performing vectorization processing on each word after word segmentation according to a text sequence to obtain a target text vector corresponding to the target text information;
s504: inputting the target text vector into a user information extraction module to obtain the user information keyword corresponding to the target text vector; the user information extraction module is trained according to different text vectors containing user information and actual user information corresponding to each text vector.
As described in the above steps S501-S504, obtaining the corresponding user information keyword according to the content of the dialog is realized. Specifically, the content of the dialog may be input into a module for converting the speech into the text, and the speech may be converted into the text by using a message flyover conversion or a hundred-degree conversion, and the like, where the target service model may include a plurality of modules, and the connection relationship between the modules may be a serial connection relationship or a parallel connection relationship, and may be set as needed. And carrying out standardization processing on the obtained preliminary text information, wherein the standardization processing mode can comprise the steps of converting words in words and sentences, cleaning and filtering dirty words, removing duplication of repeated problems and words, replacing synonyms, supplementing incomplete sentences according to sentence meanings and the like. And then performing molecule on the target text according to a preset vector machine, wherein the preset vector machine is formed by training on the basis of different dialogue data and corresponding word segmentation in the dialogue. And inputting the target text vector into a user information extraction module, and because the target text information is segmented, detecting the vocabulary of the user information in the segmented target text vector only, and then screening out the corresponding user information keywords according to the context content of the vocabulary.
In an embodiment, the step S504 of inputting the target text vector into a pre-trained user information extraction model to obtain the user information keyword corresponding to the target text vector includes:
s5041: inputting the target text vector into a word segmentation device to obtain a plurality of corresponding word vectors;
s5042: deleting irrelevant words in the target text vector according to the part of speech of each word vector to obtain a temporary text vector;
s504, 3: according to the formula
Calculating the correlation value of each target word vector and other target word vectors; wherein R (x)i) Representing the correlation value corresponding to the ith target word vector, d is a preset parameter, and xiDenotes the ith target word vector, xjRepresenting the jth target word vector, n representing the number of the target word vectors;
s5044: and obtaining the user information keywords from the target word vector according to the correlation value.
As described in steps S5041 to S5044, a specific acquisition method for the user information keyword is analyzed. That is, irrelevant words in the target text vector are deleted according to the part of speech, and since the user information is generally a noun, adjectives, exclamations, verbs, predicates, and the like can be deleted, and then the association value of each target word and other target words is calculated according to a formula, wherein the larger the calculated numerical value is, the larger the association degree of the word with other target words is, and generally, the association degree of the user information with other words in the dialog is relatively smaller, that is, words with the association value smaller than a preset association threshold value can be considered as the user information keyword. And subsequently, detecting according to the screened words to judge whether the words are user information. Therefore, each noun is prevented from being searched, time spent on retrieval is wasted, and analysis efficiency is improved.
In one embodiment, the step S4 of filtering the temporary service model according to the question information includes:
s401: calculating the similarity between the problem information and each temporary service model through a preset similarity calculation formula;
s402: and screening the target service model from the temporary service models according to the calculated similarity to carry out conversation on the user.
As described in the above steps S401-S402, selecting an appropriate temporary service model to perform a dialog on the user is realized, so that the user has a better effect on the dialog. The similarity calculation formula can be any cosine calculation formula, and then the temporary service models are screened according to the similarity between the calculated problem information and each temporary service model and the size of each similarity.
In one embodiment, the step S6 of querying a plurality of candidate user information for selection by the user according to the user information keyword includes:
s601: detecting a historical living address library of the user according to the user information key words, and detecting in a preset address library according to the key words; the user information keywords are address keywords;
s602: and screening a plurality of candidate addresses according to the detection result for the user to select.
As described in the above steps S601-S602, the screening of the information of multiple candidate users is realized. Since the user information keywords are generally the residential user information or the corporate user information of the user, the detection can be performed according to the historical residential user information base of the user to judge whether the user selects similar user information, then the user information is also screened in the preset user information base according to the keywords, and a plurality of candidate user information is obtained according to the work place of the user and the like, and the user only needs to confirm the user information, so that the time for inputting the user information by the user is greatly reduced, and the satisfaction degree of the user is improved.
In an embodiment, the step S8 of filling the target candidate user information into a service form according to a preset format includes:
s801: detecting whether the target candidate user information in the business table meets the national standard;
s802: if not, acquiring corresponding standard user information in a corresponding user information database according to the target candidate user information;
s803: and filling the standard user information into the service form.
As described in the foregoing steps S801 to S803, the target candidate user information is filled in according to the standard format, because in some services, especially related to financial loans, the format of the user information of the user in the contract is more strictly required, and the user information needs to be filled in strictly according to the national standard format, that is, whether the target candidate user information matches the national standard format is detected, if not, the corresponding standard user information is obtained in the user information database according to the target candidate user information, and then the standard user information is filled in the service form. Therefore, the user information in the service form is automatically filled in the format of the national standard.
Referring to fig. 2, the present invention also provides an AI video call-based user information filling apparatus, including:
a parameter information obtaining module 10, configured to obtain parameter information of various service models according to personal information of a user;
a parameter information input module 20, configured to input each piece of parameter information into the corresponding service model, so as to obtain a temporary service model corresponding to each service model;
a question information acquiring module 30, configured to acquire question information input by the user;
a screening module 40, configured to screen a target service model from the temporary service models according to the question information, so as to perform a conversation with the user;
the analysis module 50 is used for analyzing the content of the conversation through the target service model to obtain a corresponding user information keyword;
the query module 60 is configured to query a plurality of candidate user information according to the user information keyword for the user to select;
a receiving module 70, configured to receive target candidate user information selected by a user from the candidate user information;
and a filling module 80, configured to fill the target candidate user information into a service form according to a preset format.
In one embodiment, the parsing module 50 includes:
the input submodule is used for carrying out voice-to-word processing on the content of the conversation in the target service model to obtain preliminary text information corresponding to the content of the conversation;
the standardization processing submodule is used for carrying out standardization processing on the preliminary text information to obtain target text information;
the word segmentation sub-module is used for segmenting the target text information and vectorizing each segmented word according to the text sequence to obtain a target text vector corresponding to the target text information;
and the user information keyword acquisition submodule is used for extracting the user information keywords in the target text vector according to a preset user information extraction method.
The invention has the beneficial effects that: the method comprises the steps of selecting a proper service model to carry out conversation for a user according to personal information of the user, obtaining user information keywords from the conversation according to the corresponding service model, enabling the user information keywords to be obtained more reasonably, obtaining corresponding target candidate user information according to the user information keywords, converting the target candidate user information into a preset format, and filling the target candidate user information into a business form, so that the user information is correctly and quickly filled into the business form.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for storing various user information and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program can implement the user information filling method according to any of the above embodiments when executed by a processor.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is only a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied.
The embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the user information filling method according to any of the embodiments above may be implemented.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by hardware associated with instructions of a computer program, which may be stored on a non-volatile computer-readable storage medium, and when executed, may include processes of the above embodiments of the methods. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (10)
1. A method for filling in user information, comprising:
acquiring parameter information of various service models according to personal information of a user;
inputting the parameter information into the corresponding service models to obtain temporary service models corresponding to the service models respectively;
acquiring question information input by the user;
screening out a target service model from the temporary service models according to the problem information so as to carry out conversation on the user;
analyzing the content of the conversation through the target service model to obtain corresponding user information keywords;
inquiring a plurality of candidate user information according to the user information key words so as to be selected by the user;
receiving target candidate user information selected by a user from the candidate user information;
and filling the target candidate user information into a service form according to a preset format.
2. The method as claimed in claim 1, wherein the step of parsing the content of the dialog through the target service model to obtain the corresponding user information keyword comprises:
in the target service model, performing voice-to-word processing on the content of the conversation to obtain preliminary text information corresponding to the content of the conversation;
standardizing the preliminary text information to obtain target text information;
performing word segmentation on the target text information, and performing vectorization processing on each word after word segmentation according to a text sequence to obtain a target text vector corresponding to the target text information;
and extracting the user information keywords in the target text vector according to a preset user information extraction method.
3. The method for filling in user information according to claim 2, wherein the step of extracting the user information keyword in the target text vector according to a preset user information extraction method comprises:
inputting the target text vector into a word segmentation device to obtain a plurality of corresponding word vectors;
deleting irrelevant words in the word vectors according to the parts of speech of the word vectors to obtain a plurality of corresponding target word vectors;
according to the formula
Calculating the correlation value of each target word vector and other target word vectors; wherein R (x)i) Representing the correlation value corresponding to the ith target word vector, d is a preset parameter, and xiDenotes the ith target word vector, xjRepresenting the jth target word vector, n representing the number of the target word vectors;
and obtaining the user information keywords from the target word vector according to the correlation value.
4. The method of claim 1, wherein the step of filtering out the target service model from the temporary service models according to the question information comprises:
calculating the similarity between the problem information and each temporary service model through a preset similarity calculation formula;
and screening the target service model from the temporary service models according to the calculated similarity to carry out conversation on the user.
5. The method according to claim 1, wherein the step of querying a plurality of candidate user information for selection by the user according to the user information keyword comprises:
detecting a historical living address library of the user according to the user information key words, and detecting in a preset address library according to the key words; the user information keywords are address keywords;
and screening a plurality of candidate addresses according to the detection result for the user to select.
6. The method as claimed in claim 1, wherein the step of filling the target candidate user information into a service form according to a predetermined format comprises:
detecting whether the target candidate user information in the business table meets the national standard;
if not, acquiring corresponding standard user information in a corresponding user information database according to the target candidate user information;
and filling the standard user information into the service form.
7. A user information populating apparatus, comprising:
the parameter information acquisition module is used for acquiring parameter information of various service models according to personal information of a user;
the parameter information input module is used for inputting the parameter information into the corresponding service models to obtain temporary service models corresponding to the service models respectively;
the problem information acquisition module is used for acquiring the problem information input by the user;
the screening module is used for screening a target service model from the temporary service models according to the problem information so as to carry out conversation on the user;
the analysis module is used for analyzing the content of the conversation through the target service model to obtain a corresponding user information keyword;
the query module is used for querying a plurality of candidate user information according to the user information key words so as to be selected by the user;
the receiving module is used for receiving target candidate user information selected by a user from the candidate user information;
and the filling module is used for filling the target candidate user information into a service form according to a preset format.
8. The AI video call-based user information populating apparatus of claim 7, wherein the parsing module includes:
the input submodule is used for carrying out voice-to-word processing on the content of the conversation in the target service model to obtain preliminary text information corresponding to the content of the conversation;
the standardization processing submodule is used for carrying out standardization processing on the preliminary text information to obtain target text information;
the word segmentation sub-module is used for segmenting the target text information and vectorizing each segmented word according to the text sequence to obtain a target text vector corresponding to the target text information;
and the user information keyword acquisition submodule is used for extracting the user information keywords in the target text vector according to a preset user information extraction method.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011454835.6A CN112579751A (en) | 2020-12-10 | 2020-12-10 | User information filling method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011454835.6A CN112579751A (en) | 2020-12-10 | 2020-12-10 | User information filling method and device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112579751A true CN112579751A (en) | 2021-03-30 |
Family
ID=75131478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011454835.6A Pending CN112579751A (en) | 2020-12-10 | 2020-12-10 | User information filling method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112579751A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113672702A (en) * | 2021-08-26 | 2021-11-19 | 国家电网有限公司大数据中心 | Method, device and equipment for improving user profile information and storage medium |
| CN113935302A (en) * | 2021-12-17 | 2022-01-14 | 深圳佑驾创新科技有限公司 | Table-based PCBA test method, apparatus, device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015165172A1 (en) * | 2014-04-30 | 2015-11-05 | 小米科技有限责任公司 | Information transmission method and device in voice service |
| CN107450744A (en) * | 2017-07-13 | 2017-12-08 | 维沃移动通信有限公司 | A kind of personal data inputting method and mobile terminal |
| CN109741086A (en) * | 2018-12-11 | 2019-05-10 | 平安科技（深圳）有限公司 | A kind of generation method and equipment of computation model |
| CN111243596A (en) * | 2020-01-08 | 2020-06-05 | 中保车服科技服务股份有限公司 | Insurance information acquisition method, device and equipment based on voice recognition and storage medium |
| CN111556096A (en) * | 2020-04-01 | 2020-08-18 | 深圳壹账通智能科技有限公司 | Information pushing method, device, medium and electronic equipment |
| CN111680147A (en) * | 2020-07-07 | 2020-09-18 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and readable storage medium |
-
2020
- 2020-12-10 CN CN202011454835.6A patent/CN112579751A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015165172A1 (en) * | 2014-04-30 | 2015-11-05 | 小米科技有限责任公司 | Information transmission method and device in voice service |
| CN107450744A (en) * | 2017-07-13 | 2017-12-08 | 维沃移动通信有限公司 | A kind of personal data inputting method and mobile terminal |
| CN109741086A (en) * | 2018-12-11 | 2019-05-10 | 平安科技（深圳）有限公司 | A kind of generation method and equipment of computation model |
| CN111243596A (en) * | 2020-01-08 | 2020-06-05 | 中保车服科技服务股份有限公司 | Insurance information acquisition method, device and equipment based on voice recognition and storage medium |
| CN111556096A (en) * | 2020-04-01 | 2020-08-18 | 深圳壹账通智能科技有限公司 | Information pushing method, device, medium and electronic equipment |
| CN111680147A (en) * | 2020-07-07 | 2020-09-18 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and readable storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113672702A (en) * | 2021-08-26 | 2021-11-19 | 国家电网有限公司大数据中心 | Method, device and equipment for improving user profile information and storage medium |
| CN113935302A (en) * | 2021-12-17 | 2022-01-14 | 深圳佑驾创新科技有限公司 | Table-based PCBA test method, apparatus, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109800306B (en) | Intention analysis method, device, display terminal and computer readable storage medium | |
| CN110444198B (en) | Retrieval method, retrieval device, computer equipment and storage medium | |
| CN108595695B (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN113420113B (en) | Semantic recall model training and recall question and answer method, device, equipment and medium | |
| CN110032623B (en) | Method and device for matching question of user with title of knowledge point | |
| CN111324713B (en) | Automatic replying method and device for conversation, storage medium and computer equipment | |
| CN111223476B (en) | Method and device for extracting voice feature vector, computer equipment and storage medium | |
| CN113297366B (en) | Emotion recognition model training method, device, equipment and medium for multi-round dialogue | |
| CN110472136B (en) | Query result pushing method and device, storage medium and computer equipment | |
| CN113254620B (en) | Response method, device and equipment based on graph neural network and storage medium | |
| CN112579751A (en) | User information filling method and device and computer equipment | |
| CN112560450A (en) | Text error correction method and device | |
| CN117520523B (en) | Data processing method, device, equipment and storage medium | |
| CN114399379A (en) | Artificial intelligence-based collection behavior recognition method, device, equipment and medium | |
| CN110310169A (en) | Information-pushing method, device, equipment and medium based on interest value | |
| CN112632248A (en) | Question answering method, device, computer equipment and storage medium | |
| CN113569021B (en) | Method for classifying users, computer device and readable storage medium | |
| CN116150306A (en) | Training method of question-answering robot, question-answering method and device | |
| CN112597292B (en) | Question reply recommendation method, device, computer equipment and storage medium | |
| CN117709336A (en) | Online customer service response method and device and terminal equipment | |
| CN111309882B (en) | Method and device for realizing intelligent customer service question and answer | |
| CN114969544A (en) | Hot data-based recommended content generation method, device, equipment and medium | |
| CN113515642A (en) | Method and device for determining key breakpoint of telemarketing | |
| CN114528851A (en) | Reply statement determination method and device, electronic equipment and storage medium | |
| CN112148855A (en) | Intelligent customer service problem retrieval method, terminal and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210330 |
|
| WD01 | Invention patent application deemed withdrawn after publication |