CN110750628A - Session information interaction processing method and device, computer equipment and storage medium - Google Patents
Session information interaction processing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110750628A CN110750628A CN201910848656.1A CN201910848656A CN110750628A CN 110750628 A CN110750628 A CN 110750628A CN 201910848656 A CN201910848656 A CN 201910848656A CN 110750628 A CN110750628 A CN 110750628A
- Authority
- CN
- China
- Prior art keywords
- slot position
- slot
- information
- presumed
- session information
- 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
- 230000003993 interaction Effects 0.000 title claims abstract description 47
- 238000003672 processing method Methods 0.000 title claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 81
- 230000002452 interceptive effect Effects 0.000 claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000009826 distribution Methods 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 28
- 239000013598 vector Substances 0.000 claims description 28
- 238000012795 verification Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 11
- 238000003012 network analysis Methods 0.000 abstract 1
- 239000000284 extract Substances 0.000 description 9
- 230000001419 dependent effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 230000035558 fertility Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000010200 validation analysis 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a session information interaction processing method, a session information interaction processing device, a computer device and a storage medium based on relational network analysis. The method comprises the following steps: acquiring session information sent by a user terminal, carrying out slot position identification on the session information, and identifying slot positions and slot position values in the session information; inputting slot position information in the session information into a trained relation analysis model, and calculating the relevance between the slot position and a plurality of guess slot positions according to the guess slot positions associated with the slot position analysis; extracting the presumed slot position with the relevance reaching a threshold value, and calculating a presumed slot position value corresponding to the presumed slot position according to the information of the plurality of slot positions; determining target slot position information of a next interactive node according to the slot position information and the guess slot position information; and generating the interactive information of the next interactive node according to the target slot position information, and pushing the interactive information to the corresponding user terminal. By adopting the method, the slot position information in the session information can be accurately and effectively analyzed and predicted, so that the interactive processing efficiency of the session information can be effectively improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for processing session information interaction, a computer device, and a storage medium.
Background
With the rapid development of computer technology, many human-computer interaction systems based on task-based conversations appear, which can effectively assist users in performing some services. The rule-based groove filling method is wide in application range, a recognition template is constructed for each groove manually to form a template set by observing text data in a training expectation based on linguistic knowledge, the sequence of the template use is set after the template set is obtained, and the template is used for extracting groove information of oranges input by a user one by one.
However, the traditional method needs a lot of labor cost, and the application range is narrow, so that the method is difficult to cover various situations. And a slot filling task mode based on a classification model is also adopted, which needs to perform slot-based classification for each word, cannot effectively establish the association between slot bit values, cannot accurately and effectively analyze and predict slot bit information in session information, and causes low interaction efficiency of the session.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a session information interaction processing method, apparatus, computer device and storage medium, which can accurately and effectively identify, further analyze and predict slot information in session information, and thereby can effectively improve interaction processing efficiency of session information.
A conversation information interaction processing method comprises the following steps:
acquiring session information sent by a user terminal, wherein the session information comprises a user identifier and a service type;
identifying slot positions of the session information, and identifying slot positions and slot position values in the session information;
acquiring a trained relation analysis model according to the service type, inputting the identified slot positions and slot position values into the relation analysis model, identifying associated presumed slot positions according to the plurality of slot positions, and calculating the relevance between the slot positions and the plurality of presumed slot positions;
extracting the presumed slot position with the relevance reaching the threshold value, and calculating a presumed slot position value corresponding to the presumed slot position according to a plurality of slot position values in the session information;
determining target slot position information of a next interactive node according to the slot position information and the guess slot position information;
and generating the interactive information of the next interactive node according to the target slot position information, and pushing the interactive information to the user terminal corresponding to the user identifier.
In one embodiment, the relational analysis model has a plurality of slot importance factors deployed therein, and the identifying of the associated speculative slot from the plurality of slots comprises: extracting characteristics of the plurality of slot positions and slot position values through the relational analysis model to obtain corresponding slot position vectors; calculating the relevance among the slot position vectors according to the important factors of the slot positions; calculating the relevance between the slot position vectors and the candidate slot position according to the relevance between the slot position vectors; and extracting the candidate slot position with the relevance reaching a preset threshold value, and taking the candidate slot position as a guess slot position.
In one embodiment, the step of calculating a presumed slot value corresponding to a presumed slot according to a plurality of slot values in the session information includes: calculating probability distribution values of a plurality of elements corresponding to the presumed slot positions according to the slot positions and the slot position values; calculating confidence degrees of a plurality of elements according to the probability distribution values; and if the element with the confidence coefficient meeting the threshold does not exist, taking the guess slot position as a target slot position of the next node session.
In one embodiment, the method further comprises: if the element with the confidence coefficient meeting the threshold exists, determining the element as a presumed slot value corresponding to the presumed slot; adding the presumed slot position and the presumed slot position value into the slot position information set of the user identification; matching the slot position information set with the slot position definition table of the service type, and determining candidate slot positions according to a matching result; and calculating the correlation between the known slot position information and the candidate slot position, extracting the candidate slot position of which the correlation reaches a preset threshold value, and taking the candidate slot position as a target slot position of the next interactive node.
In one embodiment, before obtaining the trained relational analysis model, the method further includes: obtaining a plurality of sample data, and dividing the sample data into a training set and a verification set, wherein the sample data comprises a plurality of slot position information; inputting the training data into a preset network model, training the dependency relationship among a plurality of slot positions and corresponding probability distribution according to the preset network model, and generating an initial relationship analysis model; further training and verifying the initial relationship analysis model by using the verification set to obtain class probabilities corresponding to a plurality of verification data; and stopping training until the number of the class probabilities corresponding to the verification data in a preset range reaches a preset threshold value, so as to obtain the required relation analysis model.
In one embodiment, the method further comprises: when the slot position information in the slot position information set of the user identification meets a preset threshold value, acquiring product data corresponding to the service type, wherein the product data comprises attribute information; calculating the matching degree between the slot position information of the user identification and the attribute information of a plurality of product data; and acquiring product data with the matching degree reaching a threshold value of the matching degree, and pushing the product data to a user terminal corresponding to the user identifier.
A session information interaction processing apparatus, the apparatus comprising:
the data acquisition module is used for acquiring session information sent by a user terminal, wherein the session information comprises a user identifier and a service type;
the slot position identification module is used for identifying the slot position of the session information and identifying the slot position and the slot position value in the session information;
the slot position analysis module is used for acquiring a trained relation analysis model according to the service type, inputting the identified slot position and slot position values into the relation analysis model, identifying associated presumed slot positions according to a plurality of slot positions and calculating the relevance between the slot positions and the plurality of presumed slot positions; extracting the presumed slot position with the relevance reaching the threshold value, and calculating a presumed slot position value corresponding to the presumed slot position according to a plurality of slot position values in the session information; determining target slot position information of a next interactive node according to the slot position information and the guess slot position information;
and the interactive information sending module is used for generating interactive information of the next interactive node according to the target slot position information and pushing the interactive information to the user terminal corresponding to the user identifier.
In one embodiment, the apparatus further includes a product data pushing module, configured to obtain product data corresponding to the service type when slot information in a slot information set of the user identifier satisfies a preset threshold, where the product data includes attribute information; calculating the matching degree between the slot position information of the user identification and the attribute information of a plurality of product data; and acquiring product data with the matching degree reaching a threshold value of the matching degree, and pushing the product data to a user terminal corresponding to the user identifier.
A computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the session information interaction processing method provided in any one of the embodiments of the present application when executing the computer program.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the session information interaction processing method provided in any one of the embodiments of the present application.
According to the session information interaction processing method, the session information interaction processing device, the computer equipment and the storage medium, after the server obtains the session information sent by the user terminal, the slot position identification is carried out on the session information, and the slot position value in the session information are identified. The server further obtains a trained relation analysis model according to the service type of the current session, and analyzes the related presumed slot position according to the identified slot position and the slot position value through the relation analysis model, so that the related presumed slot position and the presumed slot position value can be accurately and effectively identified and analyzed. The server can further effectively determine target slot position information of a next interactive node according to the identified slot position information and the analyzed guess slot position information, generate inquiry information of the next interactive node according to the target slot position information, and send the inquiry information to the corresponding user terminal, so that the user terminal further inputs corresponding session information according to the inquiry information, interaction inquiry can be effectively carried out on the user slot position information, and accurate pushed data can be accurately and effectively pushed to the user terminal. The associated slot position information can be accurately and effectively reasoned and analyzed through the relational analysis model according to the known information, so that unnecessary conversation branches can be effectively saved, and the efficiency of interactive processing of the conversation information is effectively improved.
Drawings
FIG. 1 is a diagram illustrating an exemplary scenario of a session information interaction processing method;
FIG. 2 is a flowchart illustrating a session information interaction processing method according to an embodiment;
FIG. 3 is a schematic flow chart diagram illustrating the steps for calculating inferred bin values in one embodiment;
FIG. 4 is a schematic flow chart illustrating the steps for calculating the inferred bin value in another embodiment;
FIG. 5 is a block diagram showing the configuration of a session information interaction processing apparatus according to an embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The session information interaction processing method provided by the application can be applied to the application environment shown in fig. 1. Wherein a user terminal 102 communicates with a server 104 over a network. The user terminal 102 may send session information to the server 104, and after the server 104 obtains the session information sent by the user terminal, the server performs slot position identification on the session information to identify a slot position and a slot position value in the session information. And then acquiring a trained relation analysis model according to the service type of the current session, and analyzing the related presumed slot position according to the identified slot position and the slot position value through the relation analysis model. And then determining target slot position information of a next interactive node according to the identified slot position information and the analyzed guess slot position information, generating inquiry information of the next interactive node according to the target slot position information, and sending the inquiry information to the corresponding user terminal 102, so that the user terminal 102 further inputs corresponding session information according to the inquiry information for interaction. The user terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, a session information interaction processing method is provided, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
When the user carries out human-computer interaction through the interactive application of the corresponding user terminal, the session information can be input and sent to the corresponding server, and the server can identify the session information sent by the user and return corresponding reply information so as to carry out human-computer interaction. Such as a common intelligent advisory interaction system.
The server may obtain session information sent by the user terminal, where the session information includes a service type and may also include a user identifier. The session information may include historical session information and current session information sent by the user terminal, and reply information returned by the server to the user terminal.
And step 204, carrying out slot position identification on the session information, and identifying the slot position and the slot position value in the session information.
The slot may refer to a key information attribute in the session information, for example, the slot may be key information that the server needs to obtain; the slot value may refer to specific content corresponding to the key information attribute in the session information. For example, it may be specific key information expressed by the user. For example, the information attribute corresponding to "gender" may be a slot position, and a male may be a slot position value corresponding to the "gender" slot position. The server can pre-configure a slot position definition table corresponding to the service type, and a plurality of slot position information required by the service type is stored in the slot position definition table.
In one embodiment, the value of the slot may include an enumerable character string type, an enumerable numerical value type, a continuous numerical value type, an enumerable numerical value interval, and the like. The dependency relationship of the slot may include a form depending on other variables and independent variables. For example, in the financial field, the dependency and independent slots can be simplified, for example, the gender ratio is basically a stable ratio in 0-70 years, and the female ratio is obviously increased in >70 years, so that the gender ratio can be used as an independent variable and has no specific distribution with age.
And after the server acquires the session information sent by the user terminal, identifying slot position information in the session information. Specifically, the server may collect slot position information, where the slot position definition table stores a plurality of slot position keywords corresponding to the corresponding slot position information, where the slot position information includes slot positions and corresponding slot position values. The server can perform keyword recognition on the session information according to the slot position definition table, and recognize slot position information in the inquiry information. The server identifies the current session information and the session information adjacent to the historical session information according to the plurality of slot position keywords, extracts the text information corresponding to the slot position matched with the slot position keywords in the slot position definition table, and takes the extracted text information as the identified slot position and the corresponding slot position.
Furthermore, the server can also acquire corresponding user information according to the user identification, identify the user information, the acquired historical session information and the current session information, and identify a plurality of slot positions and corresponding slot position values. The slot and the corresponding slot location value are then complete slot information.
And step 206, acquiring the trained relational analysis model according to the service type, inputting the identified slot positions and slot position values into the relational analysis model, identifying associated presumed slot positions according to the plurality of slot positions, and calculating the relevance between the slot positions and the plurality of presumed slot positions.
And 208, extracting the presumed slot position with the relevance reaching the threshold value, and calculating a slot position value corresponding to the presumed slot position according to the plurality of slot position values in the session information.
The server may pre-construct a relational analysis model, and the relational analysis model may be an intelligent decision model based on a bayesian network.
And after the slot position information in the session information is identified by the server, acquiring a trained relational analysis model according to the service type, and inputting the identified slot position and the slot position value into the relational analysis model. The server further identifies the associated presumed slot positions according to the plurality of slot position information through a relational analysis model, and calculates the relevance between the slot positions and the plurality of presumed slot positions.
The server further extracts the presumed slot position of which the relevance reaches the threshold value, and calculates the slot position value corresponding to the presumed slot position according to the plurality of slot position values in the session information. Specifically, the server analyzes an element probability distribution value of the presumed slot according to the slot value in the session information, and determines the slot value as the slot value of the presumed slot when the slot value satisfying the threshold exists.
And step 210, determining target slot position information of the next interactive node according to the slot position information and the guessed slot position information.
And 212, generating the interactive information of the next interactive node according to the target slot position, and pushing the interactive information to the user terminal corresponding to the user identifier.
And after analyzing the slot position information and the guess slot position information in the session information through the relational analysis model, the server determines the target slot position information of the next interactive node according to the slot position information and the guess slot position information. Specifically, the slot information to be identified corresponding to the service type may be calculated according to the existing slot information and the guessed slot information, and the slot information to be identified corresponding to the service type may be determined as the target slot information of the next interactive node.
And the server further generates the interactive information of the next interactive node according to the target slot position and pushes the interactive information to the user terminal corresponding to the user identifier. The user terminal inputs corresponding session information according to the interaction information, and the server can acquire complete slot position information from the session information, so that key slot position information in the session information can be accurately and effectively identified, and the human-computer interaction efficiency is effectively improved.
For example, when slots of "gender" and "age" and corresponding "gender: male "and" age: slot values of 0-4 years of age ". Then the associated slot position 'education degree' can be analyzed through the relational analysis model, the slot position value of the slot position 'education degree' can be further analyzed to be 'not learned', then the slot position value with higher confidence coefficient can be analyzed, and further inquiry information about the slot position 'education degree' can be skipped. The target slot of the next session node is further analyzed. The associated slot position information can be accurately and effectively reasoned and analyzed through the relational analysis model according to the known information, so that unnecessary conversation branches can be effectively saved, and the efficiency of interactive processing of the conversation information is effectively improved.
In the session information interaction processing method, after the server acquires the session information sent by the user terminal, the slot position identification is carried out on the session information, and the slot position value in the session information are identified. The server further obtains a trained relation analysis model according to the service type of the current session, and analyzes the related presumed slot position according to the identified slot position and the slot position value through the relation analysis model, so that the related presumed slot position and the presumed slot position value can be accurately and effectively identified and analyzed. The server can further effectively determine target slot position information of a next interactive node according to the identified slot position information and the analyzed guess slot position information, generate inquiry information of the next interactive node according to the target slot position information, and send the inquiry information to the corresponding user terminal, so that the user terminal further inputs corresponding session information according to the inquiry information, interaction inquiry can be effectively carried out on the user slot position information, and accurate pushed data can be accurately and effectively pushed to the user terminal. The associated slot position information can be accurately and effectively reasoned and analyzed through the relational analysis model according to the known information, so that unnecessary conversation branches can be effectively saved, and the efficiency of interactive processing of the conversation information is effectively improved.
In one embodiment, identifying the associated speculative slot from the plurality of slots comprises: extracting characteristics of the plurality of slot positions and slot position values through a relational analysis model to obtain corresponding slot position vectors; calculating the relevance among the slot position vectors according to the important factors of the slot positions; calculating the relevance between the slot position vectors and the candidate slot position according to the relevance between the slot position vectors; and extracting the candidate slot position with the relevance reaching a preset threshold value, and taking the candidate slot position as a guess slot position.
Wherein, the relevant important factor of each slot position is deployed in advance in the relational analysis model.
And after receiving the session information sent by the user terminal, the server identifies the slot position of the session information and identifies the slot position and the slot position value in the session information. The server further obtains a trained relation analysis model according to the service type of the current session, and analyzes the related presumed slot position according to the identified slot position and the slot position value through the relation analysis model. Specifically, the server extracts the features of the plurality of identified slot positions and corresponding slot position values through a relational analysis model, and extracts corresponding slot position vectors.
The server further calculates the relevance among the slot position vectors according to the important factors of the slot positions deployed in the relational analysis model, and further calculates the relevance among the slot position vectors and the candidate slot positions according to the relevance among the slot position vectors. The server obtains the candidate slot position with the relevance reaching the preset threshold value and takes the candidate slot position as a guess slot position. Therefore, the server can effectively estimate the slot position information according to the identified slot position information and the analyzed slot position information.
For example, when slot types of "gender" and "age" and corresponding "gender: male "and" age: slot value of 15 years old ". Age and gender may be two important factors, among others, in determining the educational program. The associated slot position of the education degree can be analyzed through the relational analysis model, two candidate slot positions of the marital condition and the fertility condition can be directly excluded, the server acquires the associated slot position, and the slot position value of the associated slot position can be effectively analyzed.
In an embodiment, as shown in fig. 3, the step of calculating the inferred slot bit value corresponding to the inferred slot according to the plurality of slot bit values in the session information specifically includes the following steps:
and 302, calculating probability distribution values of a plurality of elements corresponding to the presumed slot positions according to the slot positions and the slot position values.
And step 304, calculating the confidence degrees of the plurality of elements according to the probability distribution value.
And step 306, if no element with the confidence coefficient meeting the threshold exists, taking the presumed slot position as a target slot position of the next node session.
After the server acquires the session information sent by the user terminal, slot position identification is carried out on the session information, and a slot position value in the session information are identified. The server further obtains a trained relation analysis model according to the service type of the current session, and analyzes the related presumed slot position according to the identified slot position and the slot position value through the relation analysis model. Specifically, the server performs feature extraction on the slot positions and the slot position values through a relational analysis model to obtain corresponding slot position vectors, and then calculates the relevance among the slot position vectors according to the important factors of the slot positions. The server calculates the relevance between the slot position vectors and the candidate slot position according to the relevance between the slot position vectors, extracts the preset slot position of which the relevance reaches a preset threshold value, and takes the extracted candidate slot position as a guess slot position.
And after the server extracts the presumed slot position according to the existing slot position information, further calculating a presumed slot position value corresponding to the presumed slot position. Specifically, the server calculates a plurality of corresponding element probability distribution values of the presumed slot according to the slot value corresponding to the slot. Wherein the slot value may be a numerical range. The server further calculates probability confidence of the plurality of slot values according to the distribution probability, and when no slot value with the probability confidence meeting the threshold exists, the slot value corresponding to the presumed slot is unknown, and the user needs to be further prompted to input corresponding answer information. The server can directly use the guess slot position as a slot target guess slot position of the next interactive node, generate corresponding interactive information according to the target guess slot position, and send the interactive information to the user terminal, so that the user inputs corresponding answer information according to the interactive information through the user terminal to carry out interaction, and the server pushes corresponding push data to the user after obtaining the required slot position information.
For example, the relational analysis model may be a bayesian network-based model, where G ═ (I, E) represents a Directed Acyclic Graph (DAG), where I represents the set of all nodes in the graph and E represents the set of directed connecting segments, and X ═ Xi (Xi) ie I is a random variable represented by a certain node I in its directed acyclic graph, if the joint probability distribution of the node X is formulated as:
P(x)＝∏i∈Ip(xi|xpa(i))
where X is called a bayesian network with respect to a directed acyclic graph G, pa (i) denotes the "cause" of node i, and the joint distribution of arbitrary random variables is obtained by multiplying the respective local conditional probability distributions:
in accordance with the above equation, the joint probability distribution of a Bayesian network can be:
where Xi corresponds to each respective "dependent" variable Xj. The difference between the above two expressions lies in the part of conditional probability, and in the bayesian network, if the dependent variable is known, some nodes will be independent of the dependent variable condition, and only the node related to the dependent variable will have conditional probability.
The method using the bayesian function can save considerable memory capacity if the number of dependencies of the joint distribution is small. For example, in the case ofIf 10 variables are stored in a conditional probability table with values of 0 or 1, an intuitive idea is that 2 must be calculated in total101024 values; however, if more than three dependent variables are not included in the 10 variables, the conditional probability table of the Bayesian network only needs to calculate 10 × 2 at most3It is sufficient if 80 values are used. Another advantage of the bayesian network is that it is easier to know whether the conditions between the variables are independent or dependent on the local distribution (local distribution) to obtain the joint distribution of all random variables.
For example, if slot information of "age" and "gender" is known, a correlation between "age" and "gender" and "education level" is analyzed. The unknown presumed slot position and its probability distribution value can be deduced according to the known slot position information. If E is the educational level, a is age, G is gender, wherein age and gender are two important factors in determining the educational program, i.e., E ═ a, G. E, A, G form a directed acyclic graph.
The formula for calculating the probability distribution values of the plurality of elements may be:
P(E)＝∏i∈Ip(Ei|A,G)
wherein E may be the educational level, A may be the age, and G may be the gender. A, G may be two independent variables. G can take two values, namely G0 and G1.
As shown in table 1 below, the probability distribution values for the "gender" slot may be as follows:
| value of sex | Probability of | Description of the invention |
| G0 | 0.5085 | For male |
| G1 | 0.4915 | Woman |
TABLE 1
As shown in table 2 below, there may be 20 values for the "age" slot, i.e., a0-a19, and the probability distribution values may be as follows:
| age value | Probability of | Description of the invention |
| A0 | 0.0585 | 0-4 years old |
| A1 | 0.0548 | 5-9 years old |
| … | … | … |
| A20 | 0.000001 | >Age of 100 years old |
TABLE 2
As shown in table 3 below, the probability distribution values for the "educational level" slots may be as follows:
| degree of education | Go on to study | Primary school | Middle school | High school | Chinese patent drug | Major project | University | Research student |
| E0 | E1 | E2 | E3 | E4 | E5 | E6 | E7 |
Table 3 CPD (conditional probability distribution) relationships of the "gender" slot, the "age" slot, and the "education level" slot can be shown in table 4 below:
| E0 | E1 | E2 | E3 | E4 | E5 | E6 | E7 | |
| G0，A0 | 0.99 | 0.01 | 0 | 0 | 0 | 0 | 0 | 0 |
| G0，A1 | 0.04 | 0.95 | 0.01 | 0 | 0 | 0 | 0 | 0 |
| … | ||||||||
| G1,A19 | 0.66 | 0.3 | 0.03 | 0.01 | 0 | 0 | 0 | 0 |
TABLE 4
Calculated by the above formula and table data, at the known slot position: sex: male, age: e0 was 0.99 at age 0-4. Wherein the set threshold may be 0.95. Therefore, if the confidence of E0 satisfies the preset threshold, it can be found that the slot value satisfying the confidence of the "educated level" is "not going to primary school". The server can skip the problem corresponding to the slot without further sending inquiry information corresponding to the slot of education degree to the user terminal. The server can accurately and effectively deduce and analyze the presumed slot position and the corresponding presumed slot position value according to the known slot position information through the relational analysis model, so that the corresponding interaction information can be effectively generated according to the target presumed slot position, and the interaction efficiency is improved.
In an embodiment, as shown in fig. 4, the step of calculating the inferred slot bit value corresponding to the inferred slot according to the plurality of slot bit values in the session information specifically includes the following steps:
And step 406, matching the slot position information set with the slot position definition table of the service type, and determining candidate slot positions according to a matching result.
And 408, calculating the correlation between the known slot position information and the candidate slot position, extracting the candidate slot position with the correlation reaching a preset threshold value, and taking the candidate slot position as a target slot position of the next interactive node.
After the server acquires the session information sent by the user terminal, slot position identification is carried out on the session information, and a slot position value in the session information are identified. The server further obtains a trained relation analysis model according to the service type of the current session, and analyzes the related presumed slot position according to the identified slot position and the slot position value through the relation analysis model.
Specifically, the server performs feature extraction on the slot positions and the slot position values through a relational analysis model to obtain corresponding slot position vectors, and then calculates the relevance among the slot position vectors according to the important factors of the slot positions. The server calculates the relevance between the slot position vectors and the candidate slot position according to the relevance between the slot position vectors, extracts the preset slot position of which the relevance reaches a preset threshold value, and takes the extracted candidate slot position as a guess slot position.
And after the server extracts the presumed slot position according to the existing slot position information, further calculating a presumed slot position value corresponding to the presumed slot position. Specifically, the server calculates a plurality of corresponding element probability distribution values of the presumed slot according to the slot value corresponding to the slot. The server further calculates probability confidence of the plurality of slot values according to the distribution probability, and when no slot value with the probability confidence meeting the threshold exists, the slot value corresponding to the presumed slot is unknown, and the user needs to be further prompted to input corresponding answer information. The server can directly use the speculation slot as a slot target speculation slot of the next interactive node.
If the element with the confidence coefficient meeting the threshold exists, the server determines the element as a guess slot value corresponding to the guess slot. The server may pre-configure a slot position definition table corresponding to the service type, where the slot position definition table stores a plurality of slot position information required by the service type. The server may pre-establish a slot information set corresponding to the user identifier, and after analyzing and obtaining the known slot information corresponding to the user identifier, the server adds the identified slot information and the analyzed and obtained presumed slot information to the slot information set corresponding to the user identifier.
The server further matches the slot position information set with the slot position definition table of the service type, and determines the candidate slot position according to the matching result. For example, the server may match the slot information in the slot definition table of the service type according to the known slot information in the slot information set, identify the remaining unknown slot information in the slot definition table, and determine the unknown slot information as a candidate slot.
And the server calculates the correlation between the plurality of pieces of known slot position information and the candidate slot positions, extracts the candidate slot positions of which the correlation reaches a preset threshold value, and takes the candidate slot positions as the target slot positions of the next interactive node.
The server can further generate inquiry information of the next interactive node according to the target slot position information and send the inquiry information to the corresponding user terminal, so that the user terminal further inputs corresponding session information according to the inquiry information, interactive inquiry can be effectively carried out on the slot position information of the user, and accurate pushed data can be accurately and effectively pushed to the user terminal. The associated slot position information can be accurately and effectively reasoned and analyzed through the relational analysis model according to the known information, so that unnecessary conversation branches can be effectively saved, and the efficiency of interactive processing of the conversation information is effectively improved.
In one embodiment, before obtaining the trained relational analysis model, the server further includes a step of constructing the relational analysis model, which specifically includes: obtaining a plurality of sample data, and dividing the sample data into a training set and a verification set, wherein the sample data comprises a plurality of slot position information; inputting training data into a preset network model, training the dependency relationship among a plurality of slot positions and corresponding probability distribution according to the preset network model, and generating an initial relationship analysis model; further training and verifying the initial relationship analysis model by using a verification set to obtain class probabilities corresponding to a plurality of verification data; and stopping training until the number of the class probabilities corresponding to the verification data in the preset range reaches a preset threshold value, and obtaining the required relation analysis model.
Before the server acquires the preset relation analysis model, the relation analysis model can be constructed and trained in advance. Specifically, the server may obtain a large amount of sample data from the local database or the third-party database in advance, and generate a training set and a validation set from the large amount of sample data. The sample data in the training set can be a plurality of pieces of slot position information after manual marking, and the verification set is a plurality of pieces of unmarked slot position information.
The server firstly carries out data cleaning and data preprocessing on training sample data in a training set to obtain a plurality of preprocessed slot position information. The server inputs the slot position information into a preset network model, wherein the preset network model can be a model based on a Bayesian network. And the server trains and learns the dependency relationship among the plurality of slot positions and the probability distribution intervals corresponding to the plurality of slot position information according to the initial network model, and trains to obtain an initial relationship analysis model.
The server further trains and verifies the generated initial relationship analysis model by using the plurality of slot position information in the verification set to obtain the class probability corresponding to the plurality of verification data. And stopping training until the number of the class probabilities corresponding to the verification data in the preset range reaches a preset threshold value, so as to obtain the required relation analysis model. By analyzing and training a large amount of training data, the dependency relationship among a plurality of slot positions can be effectively analyzed, a relationship analysis model is effectively constructed, and then the associated slot position information can be accurately and effectively analyzed by inference according to the known information.
In one embodiment, the method further comprises: when the slot position information in the slot position information set of the user identification meets a preset threshold value, acquiring product data corresponding to the service type, wherein the product data comprises attribute information; calculating the matching degree between the slot position information of the user identification and the attribute information of the plurality of product data; and acquiring product data with the matching degree reaching a threshold value of the matching degree, and pushing the product data to a user terminal corresponding to the user identifier.
After the server acquires the session information sent by the user terminal, slot position identification is carried out on the session information, and a slot position value in the session information are identified. The server further obtains a trained relation analysis model according to the service type of the current session, and analyzes the related presumed slot position according to the identified slot position and the slot position value through the relation analysis model, so that the related presumed slot position and the presumed slot position value can be accurately and effectively identified and analyzed. The server can further effectively determine target slot position information of a next interactive node according to the identified slot position information and the analyzed guess slot position information, generate inquiry information of the next interactive node according to the target slot position information, and send the inquiry information to the corresponding user terminal, so that the user terminal further inputs corresponding session information according to the inquiry information, and interaction inquiry can be effectively carried out on the user slot position information.
In the process of interaction between the user terminal and the server, the server continuously acquires slot position information corresponding to the user identifier and adds the slot position information to a slot position information set of the user identifier.
When the server detects that the slot position information in the slot position information set of the user identification meets a preset threshold value, the known slot position information corresponding to the user identification meets the slot position information amount required by the service type. And the server acquires product data corresponding to the service type, wherein the product data comprises corresponding attribute information. For example, the product data may include financial product data, insurance product data, and the like. And then the corresponding product data is matched according to the slot position information of the user identification. Specifically, the server may calculate a matching degree between the slot position information of the user identifier and the attribute information of the plurality of product data, obtain product data of which the matching degree reaches a threshold value of the matching degree, and push the product data to the user terminal corresponding to the user identifier. The associated slot position information can be accurately and effectively reasoned and analyzed through the relational analysis model according to the known information, so that unnecessary conversation branches can be effectively saved, the efficiency of interactive processing of conversation information is effectively improved, and the product data with high matching degree can be accurately pushed to a user.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 5, there is provided a session information interaction processing apparatus including: a data obtaining module 502, a slot identifying module 504, a slot analyzing module 506, and an interaction information sending module 508, wherein:
a data obtaining module 502, configured to obtain session information sent by a user terminal, where the session information includes a user identifier and a service type;
a slot position identification module 504, configured to perform slot position identification on the session information, and identify a slot position and a slot position value in the session information;
the slot position analysis module 506 acquires a trained relation analysis model according to the service type, inputs the identified slot position and slot position value into the relation analysis model, identifies associated presumed slot positions according to the slot positions, and calculates the association between the slot position and the presumed slot positions; extracting the presumed slot position with the relevance reaching the threshold value, and calculating a presumed slot position value corresponding to the presumed slot position according to a plurality of slot position values in the session information; determining target slot position information of a next interactive node according to the slot position information and the guess slot position information;
and the interaction information sending module 508 is configured to generate interaction information of a next interaction node according to the target slot position information, and push the interaction information to the user terminal corresponding to the user identifier.
In one embodiment, the slot analysis module 506 is further configured to perform feature extraction on the plurality of slots and the slot values through the relational analysis model to obtain corresponding slot vectors; calculating the relevance among the slot position vectors according to the important factors of the slot positions; calculating the relevance between the slot position vectors and the candidate slot position according to the relevance between the slot position vectors; and extracting the candidate slot position with the relevance reaching a preset threshold value, and taking the candidate slot position as a guess slot position.
In one embodiment, the slot analyzing module 506 is further configured to calculate probability distribution values of a plurality of elements corresponding to the presumed slot according to the plurality of slots and the slot values; calculating confidence degrees of the plurality of elements according to the probability distribution values; and if no element with the confidence coefficient meeting the threshold exists, taking the guessed slot position as a target slot position of the next node session.
In one embodiment, the slot analysis module 506 is further configured to determine an element as a speculative slot value corresponding to the speculative slot if the element exists whose confidence level satisfies the threshold; adding the presumed slot position and the presumed slot position value into a slot position information set of the user identification; matching the slot position information set with a slot position definition table of the service type, and determining candidate slot positions according to a matching result; and calculating the correlation between the known slot position information and the candidate slot position, extracting the candidate slot position with the correlation reaching a preset threshold value, and taking the candidate slot position as a target slot position of the next interactive node.
In one embodiment, the apparatus further includes a model building module, configured to obtain a plurality of sample data, divide the sample data into a training set and a verification set, where the sample data includes a plurality of slot position information; inputting training data into a preset network model, training the dependency relationship among a plurality of slot positions and corresponding probability distribution according to the preset network model, and generating an initial relationship analysis model; further training and verifying the initial relationship analysis model by using a verification set to obtain class probabilities corresponding to a plurality of verification data; and stopping training until the number of the class probabilities corresponding to the verification data in the preset range reaches a preset threshold value, and obtaining the required relation analysis model.
In one embodiment, the apparatus further includes a product data pushing module, configured to obtain product data corresponding to the service type when slot position information in a slot position information set identified by the user meets a preset threshold, where the product data includes attribute information; calculating the matching degree between the slot position information of the user identification and the attribute information of the plurality of product data; and acquiring product data with the matching degree reaching a threshold value of the matching degree, and pushing the product data to a user terminal corresponding to the user identifier.
For the specific definition of the session information interaction processing device, reference may be made to the above definition of the session information interaction processing method, which is not described herein again. The modules in the session information interaction processing device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing 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 internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data such as session information, slot position information, product data, slot position definition tables 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 is executed by a processor to implement the steps of the session information interaction processing method provided in any one of the embodiments of the present application.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely 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 apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, implements the steps of the session information interaction processing method provided in any one of the embodiments of the present application.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. 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 Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A conversation information interaction processing method comprises the following steps:
acquiring session information sent by a user terminal, wherein the session information comprises a user identifier and a service type;
identifying slot positions of the session information, and identifying slot positions and slot position values in the session information;
acquiring a trained relation analysis model according to the service type, inputting the identified slot positions and slot position values into the relation analysis model, identifying associated presumed slot positions according to the plurality of slot positions, and calculating the relevance between the slot positions and the plurality of presumed slot positions;
extracting the presumed slot position with the relevance reaching the threshold value, and calculating a presumed slot position value corresponding to the presumed slot position according to a plurality of slot position values in the session information;
determining target slot position information of a next interactive node according to the slot position information and the guess slot position information;
and generating the interactive information of the next interactive node according to the target slot position information, and pushing the interactive information to the user terminal corresponding to the user identifier.
2. The method of claim 1, wherein a plurality of slot importance factors are deployed in the relational analysis model, and wherein identifying an associated speculative slot from the plurality of slots comprises:
extracting characteristics of the plurality of slot positions and slot position values through the relational analysis model to obtain corresponding slot position vectors;
calculating the relevance among the slot position vectors according to the important factors of the slot positions;
calculating the relevance between the slot position vectors and the candidate slot position according to the relevance between the slot position vectors;
and extracting the candidate slot position with the relevance reaching a preset threshold value, and taking the candidate slot position as a guess slot position.
3. The method of claim 1, wherein the step of calculating a derived slot value corresponding to a derived slot from the plurality of slot values in the session information comprises:
calculating probability distribution values of a plurality of elements corresponding to the presumed slot positions according to the slot positions and the slot position values;
calculating confidence degrees of a plurality of elements according to the probability distribution values;
and if the element with the confidence coefficient meeting the threshold does not exist, taking the guess slot position as a target slot position of the next node session.
4. The method of claim 3, further comprising:
if the element with the confidence coefficient meeting the threshold exists, determining the element as a presumed slot value corresponding to the presumed slot;
adding the presumed slot position and the presumed slot position value into the slot position information set of the user identification;
matching the slot position information set with the slot position definition table of the service type, and determining candidate slot positions according to a matching result;
and calculating the correlation between the known slot position information and the candidate slot position, extracting the candidate slot position of which the correlation reaches a preset threshold value, and taking the candidate slot position as a target slot position of the next interactive node.
5. The method of claim 1, further comprising, prior to obtaining the trained relational analysis model:
obtaining a plurality of sample data, and dividing the sample data into a training set and a verification set, wherein the sample data comprises a plurality of slot position information;
inputting the training data into a preset network model, training the dependency relationship among a plurality of slot positions and corresponding probability distribution according to the preset network model, and generating an initial relationship analysis model;
further training and verifying the initial relationship analysis model by using the verification set to obtain class probabilities corresponding to a plurality of verification data;
and stopping training until the number of the class probabilities corresponding to the verification data in a preset range reaches a preset threshold value, so as to obtain the required relation analysis model.
6. The method according to any one of claims 1 to 5, further comprising:
when the slot position information in the slot position information set of the user identification meets a preset threshold value, acquiring product data corresponding to the service type, wherein the product data comprises attribute information;
calculating the matching degree between the slot position information of the user identification and the attribute information of a plurality of product data;
and acquiring product data with the matching degree reaching a threshold value of the matching degree, and pushing the product data to a user terminal corresponding to the user identifier.
7. A session information interaction processing apparatus, the apparatus comprising:
the data acquisition module is used for acquiring session information sent by a user terminal, wherein the session information comprises a user identifier and a service type;
the slot position identification module is used for identifying the slot position of the session information and identifying the slot position and the slot position value in the session information;
the slot position analysis module is used for acquiring a trained relation analysis model according to the service type, inputting the identified slot position and slot position values into the relation analysis model, identifying associated presumed slot positions according to a plurality of slot positions and calculating the relevance between the slot positions and the plurality of presumed slot positions; extracting the presumed slot position with the relevance reaching the threshold value, and calculating a presumed slot position value corresponding to the presumed slot position according to a plurality of slot position values in the session information; determining target slot position information of a next interactive node according to the slot position information and the guess slot position information;
and the interactive information sending module is used for generating interactive information of the next interactive node according to the target slot position information and pushing the interactive information to the user terminal corresponding to the user identifier.
8. The apparatus according to claim 7, further comprising a product data pushing module, configured to obtain product data corresponding to the service type when slot information in a slot information set of the user identifier satisfies a preset threshold, where the product data includes attribute information; calculating the matching degree between the slot position information of the user identification and the attribute information of a plurality of product data; and acquiring product data with the matching degree reaching a threshold value of the matching degree, and pushing the product data to a user terminal corresponding to the user identifier.
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 (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910848656.1A CN110750628A (en) | 2019-09-09 | 2019-09-09 | Session information interaction processing method and device, computer equipment and storage medium |
| PCT/CN2020/087775 WO2021047189A1 (en) | 2019-09-09 | 2020-04-29 | Method and apparatus for interactive session information processing, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910848656.1A CN110750628A (en) | 2019-09-09 | 2019-09-09 | Session information interaction processing method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110750628A true CN110750628A (en) | 2020-02-04 |
Family
ID=69276096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910848656.1A Pending CN110750628A (en) | 2019-09-09 | 2019-09-09 | Session information interaction processing method and device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110750628A (en) |
| WO (1) | WO2021047189A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021047189A1 (en) * | 2019-09-09 | 2021-03-18 | 深圳壹账通智能科技有限公司 | Method and apparatus for interactive session information processing, computer device and storage medium |
| CN116150221A (en) * | 2022-10-09 | 2023-05-23 | 浙江博观瑞思科技有限公司 | Information interaction method and system for service of enterprise E-business operation management |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133345A (en) * | 2017-05-22 | 2017-09-05 | 北京百度网讯科技有限公司 | Exchange method and device based on artificial intelligence |
| US20180114453A1 (en) * | 2016-10-21 | 2018-04-26 | Vedantu Innovations Pvt Ltd. | System for measuring effectiveness of an interactive online learning system |
| CN108153902A (en) * | 2018-01-16 | 2018-06-12 | 和美（深圳）信息技术股份有限公司 | More wheel session interaction method, apparatus, computer equipment and storage medium |
| CN109241251A (en) * | 2018-07-27 | 2019-01-18 | 众安信息技术服务有限公司 | A kind of session interaction method |
| CN109785833A (en) * | 2019-01-02 | 2019-05-21 | 苏宁易购集团股份有限公司 | Human-computer interaction audio recognition method and system for smart machine |
| CN109901896A (en) * | 2018-12-06 | 2019-06-18 | 华为技术有限公司 | Multi-task processing method in a kind of man-machine interactive system and man-machine interactive system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750628A (en) * | 2019-09-09 | 2020-02-04 | 深圳壹账通智能科技有限公司 | Session information interaction processing method and device, computer equipment and storage medium |
-
2019
- 2019-09-09 CN CN201910848656.1A patent/CN110750628A/en active Pending
-
2020
- 2020-04-29 WO PCT/CN2020/087775 patent/WO2021047189A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180114453A1 (en) * | 2016-10-21 | 2018-04-26 | Vedantu Innovations Pvt Ltd. | System for measuring effectiveness of an interactive online learning system |
| CN107133345A (en) * | 2017-05-22 | 2017-09-05 | 北京百度网讯科技有限公司 | Exchange method and device based on artificial intelligence |
| CN108153902A (en) * | 2018-01-16 | 2018-06-12 | 和美（深圳）信息技术股份有限公司 | More wheel session interaction method, apparatus, computer equipment and storage medium |
| CN109241251A (en) * | 2018-07-27 | 2019-01-18 | 众安信息技术服务有限公司 | A kind of session interaction method |
| CN109901896A (en) * | 2018-12-06 | 2019-06-18 | 华为技术有限公司 | Multi-task processing method in a kind of man-machine interactive system and man-machine interactive system |
| CN109785833A (en) * | 2019-01-02 | 2019-05-21 | 苏宁易购集团股份有限公司 | Human-computer interaction audio recognition method and system for smart machine |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021047189A1 (en) * | 2019-09-09 | 2021-03-18 | 深圳壹账通智能科技有限公司 | Method and apparatus for interactive session information processing, computer device and storage medium |
| CN116150221A (en) * | 2022-10-09 | 2023-05-23 | 浙江博观瑞思科技有限公司 | Information interaction method and system for service of enterprise E-business operation management |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021047189A1 (en) | 2021-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110598206B (en) | Text semantic recognition method and device, computer equipment and storage medium | |
| CN108595695B (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN108427707B (en) | Man-machine question and answer method, device, computer equipment and storage medium | |
| CN110765265B (en) | Information classification extraction method and device, computer equipment and storage medium | |
| CN108628974B (en) | Public opinion information classification method and device, computer equipment and storage medium | |
| CN110457431B (en) | Knowledge graph-based question and answer method and device, computer equipment and storage medium | |
| CN109446302B (en) | Question-answer data processing method and device based on machine learning and computer equipment | |
| CN108491511B (en) | Data mining method and device based on graph data and model training method and device | |
| CN110334179B (en) | Question-answer processing method, device, computer equipment and storage medium | |
| CN108897734B (en) | User portrait generation method, device, computer equipment and storage medium | |
| CN109800307B (en) | Product evaluation analysis method and device, computer equipment and storage medium | |
| CN110008250B (en) | Social security data processing method and device based on data mining and computer equipment | |
| CN110909137A (en) | Information pushing method and device based on man-machine interaction and computer equipment | |
| CN110569500A (en) | Text semantic recognition method and device, computer equipment and storage medium | |
| CN111079056A (en) | Method, device, computer equipment and storage medium for extracting user portrait | |
| CN111192025A (en) | Occupational information matching method and device, computer equipment and storage medium | |
| CN113157863A (en) | Question and answer data processing method and device, computer equipment and storage medium | |
| CN111400340B (en) | Natural language processing method, device, computer equipment and storage medium | |
| CN109460541B (en) | Vocabulary relation labeling method and device, computer equipment and storage medium | |
| CN112766319A (en) | Dialogue intention recognition model training method and device, computer equipment and medium | |
| CN111583911A (en) | Speech recognition method, device, terminal and medium based on label smoothing | |
| CN110597951A (en) | Text parsing method and device, computer equipment and storage medium | |
| CN112035611A (en) | Target user recommendation method and device, computer equipment and storage medium | |
| WO2021047189A1 (en) | Method and apparatus for interactive session information processing, computer device and storage medium | |
| CN110175273A (en) | Text handling method, device, computer readable storage medium and computer equipment |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200204 |