CN110727773B - Information providing method and device - Google Patents
Information providing method and device Download PDFInfo
- Publication number
- CN110727773B CN110727773B CN201910962487.4A CN201910962487A CN110727773B CN 110727773 B CN110727773 B CN 110727773B CN 201910962487 A CN201910962487 A CN 201910962487A CN 110727773 B CN110727773 B CN 110727773B
- Authority
- CN
- China
- Prior art keywords
- filling parameter
- user
- information
- service scene
- new
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 81
- 230000011218 segmentation Effects 0.000 claims description 50
- 230000004044 response Effects 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000010606 normalization Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000003993 interaction Effects 0.000 abstract description 9
- 230000008569 process Effects 0.000 description 13
- 230000009471 action Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010006 flight Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static 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
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an information providing method and device, wherein the method comprises the following steps: and aiming at the first set, judging whether the number of each data item in the first set is larger than a first threshold value, if so, calculating the information gain ratio of each filling parameter in the filling parameter list, selecting an inquiry template corresponding to the filling parameter with the largest information gain ratio to inquire the user so as to obtain filling parameter information, deleting the data items which are not matched with the filling parameter information in the first set to obtain a new first set, deleting the filling parameter with the largest information gain ratio in the filling parameter list to obtain a new filling parameter list, judging whether the number of each data item in the new first set is larger than the first threshold value again until the number of the data items is not larger than the first threshold value, and providing each data item in the new first set for the user. The method provided by the invention inquires the user by selecting the filling parameter with the largest information gain ratio each time, reduces the number of times of interaction with the user and improves the service efficiency.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an information providing method and device.
Background
With the progress of science and technology, the research of robots has gradually gone out of the industrial field and expanded to the industries of medical treatment, health care, family, service and the like, and the requirements of people on the robots are also improved from simple and repeated mechanical actions to intelligent robots with anthropomorphic question answering and autonomy, so that human-computer interaction becomes an important factor for determining the development of the intelligent robots. In the process of man-machine interaction between a user and the robot, the robot determines a corresponding service scene according to voice data of the user, searches a result corresponding to the voice data according to parameter information of each limited parameter in the acquired service scene, and provides the searched result for the user.
In the existing information providing method, for the acquisition of parameter information of all limited parameters, questions are asked to a user according to a preset sequence, and corresponding parameter information is acquired from answers of the user; by applying the existing information providing method, the query sequence depends on the early manual presetting, the passenger is queried according to the preset sequence, and the service scene with large data volume needs to be queried with the user for multiple times, so that the service efficiency is low, and the use experience effect of the user is poor.
Disclosure of Invention
The technical problem to be solved by the invention is to provide an information providing method, which queries the user by selecting the filling limiting parameter with the maximum current information gain ratio, thereby reducing the interaction times with the user and improving the service efficiency and the user experience.
The invention also provides an information providing device for ensuring the realization and the application of the method in practice.
An information providing method comprising:
collecting voice data of a user, and determining a target service scene from each preset service scene according to the voice data;
acquiring a scene template of the target service scene; the scene template comprises a mandatory filling parameter list and a selective filling parameter list;
acquiring necessary filling parameter information of each necessary filling parameter contained in the necessary filling parameter list;
searching data items which accord with all the filling parameter information, and forming a first set by the searched data items;
judging whether the number of each data item in the first set is greater than a preset first threshold value or not;
when the number of each data item in the first set is larger than the first threshold value, calculating an information gain ratio of each filling parameter in the filling parameter list, and inquiring the user according to a preset inquiry template corresponding to the filling parameter with the largest information gain ratio;
when response information of the user responding to the inquiry is received, acquiring filling parameter information in the response information, deleting data items which are not matched with the filling parameter information in the first set to obtain a new first set, and deleting filling parameters with the largest information gain ratio in the filling parameter list to obtain a new filling parameter list;
whether the number of each data item in the new first set is larger than the first threshold value or not is judged again on the basis of the new first set and the new filling parameter list, and when the number of each data item in the new first set is larger than the first threshold value, the information gain ratio of each filling parameter in the new filling parameter list is calculated until the finally determined number of each data item in the new first set is not larger than the first threshold value;
and providing each data item in the finally determined new first set to the user.
Optionally, in the method, determining a target service scenario from each preset service scenario according to the voice data includes:
recognizing the voice data to obtain voice characters corresponding to the voice data;
performing word segmentation on the voice characters according to a preset word segmentation strategy to obtain word segmentation results of the voice characters; the word segmentation result comprises a plurality of words;
acquiring each preset service scene;
for each service scene, matching each vocabulary in the word segmentation result with each keyword corresponding to the service scene to obtain a matching score corresponding to the service scene;
determining the matching score with the highest score, and comparing the matching score with the highest score with a preset matching threshold;
and if the matching score with the highest score is larger than the matching threshold, determining the service scene corresponding to the matching score with the highest score as a target service scene.
The above method, optionally, further includes:
if the matching score with the highest score is not larger than the matching threshold, inputting each vocabulary in the word segmentation result into a pre-constructed word vector model to obtain a word vector of each vocabulary;
carrying out normalization processing on the word vector of each vocabulary to obtain a normalized word vector of each vocabulary;
for each service scene, performing similarity calculation on each normalized word vector and the word vector of each keyword corresponding to the service scene to obtain similarity corresponding to the service scene;
determining the similarity with the maximum value, and comparing the similarity with the maximum value with a preset similarity threshold;
and if the similarity with the maximum value is greater than the similarity threshold, determining the service scene corresponding to the similarity with the maximum value as a target service scene.
Optionally, the above method, where obtaining the mandatory fill parameter information of each mandatory fill parameter included in the mandatory fill parameter list includes:
inquiring the user according to each necessary filling parameter in the necessary filling parameter list and a preset inquiry template corresponding to the necessary filling parameter;
and when response information of the user responding to the inquiry is received, acquiring the necessary filling parameter information in the response information.
The method above, optionally, after providing the first set to the user, further includes:
acquiring the preference of the user and historical data corresponding to the target service scene;
and providing services to the user according to the historical data and the preference of the user.
An information providing apparatus comprising:
the system comprises a collecting unit, a processing unit and a processing unit, wherein the collecting unit is used for collecting voice data of a user and determining a target service scene from each preset service scene according to the voice data;
a first obtaining unit, configured to obtain a scene template of the target service scene; the scene template comprises a mandatory filling parameter list and a selective filling parameter list;
a second obtaining unit, configured to obtain the necessary padding parameter information of each necessary padding parameter included in the necessary padding parameter list;
the searching unit is used for searching the data items which accord with all the necessary filling parameter information and forming a first set by the searched data items;
the judging unit is used for judging whether the number of each data item in the first set is greater than a preset first threshold value or not;
the first calculating unit is used for calculating the information gain ratio of each filling parameter in the filling parameter list when the number of each data item in the first set is larger than the first threshold value, and inquiring the user according to a preset inquiry template corresponding to the filling parameter with the largest information gain ratio;
a deleting unit, configured to, when response information that the user responds to the query is received, obtain filling parameter information in the response information, delete a data item in the first set that does not match the filling parameter information, obtain a new first set, delete a filling parameter with a largest information gain ratio in the filling parameter list, and obtain a new filling parameter list;
a second calculating unit, configured to re-determine, based on the new first set and the new padding parameter list, whether the number of each data item in the new first set is greater than the first threshold, and when the number of each data item in the new first set is greater than the first threshold, calculate an information gain ratio of each padding parameter in the new padding parameter list until the finally determined number of each data item in the new first set is not greater than the first threshold;
a first providing unit, configured to provide each data item in the finally determined new first set to the user.
The above apparatus, optionally, the collecting unit includes:
the recognition subunit is used for recognizing the voice data and obtaining voice characters corresponding to the voice data;
the word segmentation subunit is used for segmenting the voice characters according to a preset word segmentation strategy to obtain word segmentation results of the voice characters; the word segmentation result comprises a plurality of words;
the first acquiring subunit is used for acquiring each preset service scene;
the matching subunit is used for matching each vocabulary in the word segmentation result with each keyword corresponding to the service scene aiming at each service scene to obtain a matching score corresponding to the service scene;
the first comparison subunit is used for determining the matching score with the highest score and comparing the matching score with the highest score with a preset matching threshold;
and the first determining subunit is configured to determine, if the matching score with the highest score is greater than the matching threshold, the service scenario corresponding to the matching score with the highest score as the target service scenario.
The above apparatus, optionally, the collecting unit includes:
the input subunit is configured to, if the matching score with the highest score is not greater than the matching threshold, input each vocabulary in the word segmentation result into a pre-constructed word vector model to obtain a word vector of each vocabulary;
the normalization subunit is used for performing normalization processing on the word vector of each vocabulary to obtain a normalized word vector of each vocabulary;
the calculation subunit is configured to, for each service scene, perform similarity calculation on each normalized word vector and the word vector of each keyword corresponding to the service scene to obtain a similarity corresponding to the service scene;
the second comparison subunit is used for determining the similarity with the maximum numerical value and comparing the similarity with a preset similarity threshold value;
and a second determining subunit, configured to determine, if the similarity with the largest value is greater than the similarity threshold, the service scene corresponding to the similarity with the largest value as a target service scene.
The above apparatus, optionally, the second obtaining unit includes:
the inquiry subunit is configured to inquire the user according to a preset inquiry template corresponding to the mandatory fill parameter for each mandatory fill parameter in the mandatory fill parameter list;
and the second acquisition subunit is used for acquiring the necessary filling parameter information in the response information when receiving the response information of the user responding to the inquiry.
The above apparatus, optionally, further comprises:
a third obtaining unit, configured to obtain a preference of the user and historical data corresponding to the target service scenario;
and the second providing unit is used for providing services for the user according to the historical data and the preference of the user.
A storage medium comprising stored instructions, wherein the instructions, when executed, control a device on which the storage medium resides to perform the above-described information providing method.
An electronic device comprising a memory, and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by the one or more processors to perform the above-described information providing method.
Compared with the prior art, the invention has the following advantages:
the invention provides an information providing method, which comprises the following steps: collecting voice data of a user, determining a target service scene template corresponding to the voice data according to the voice data, acquiring filling parameter information of each filling parameter in a filling parameter list contained in the target service scene template, searching data items conforming to all filling parameter information, forming the searched data items into a first set, comparing the number of the data items in the first set with a preset first threshold value, if the number of the data items in the first set is greater than the preset first threshold value, calculating an information gain ratio of each filling parameter in the filling parameter list, selecting an inquiry template corresponding to the filling parameter with the largest information gain ratio to inquire the user to obtain filling parameter information corresponding to the filling parameter, deleting the data items in the first set which are not matched with the filling parameter information to obtain a new first set, and deleting the filling parameters with the largest information gain ratio in the filling parameter list to obtain a new filling parameter list, comparing the number of each data item in the new first set with the first threshold value until the number of each data item in the new first set is not more than the first threshold value, and providing each data item in the new first set for a user. According to the information providing method provided by the invention, the user is inquired by selecting the filling parameter with the largest information gain ratio every time, and the information required by the user is quickly and accurately determined, so that the interaction times with the user are reduced, and the service efficiency and the user experience are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method of providing information according to the present invention;
FIG. 2 is a flow chart of another method of an information providing method according to the present invention;
FIG. 3 is a schematic structural diagram of an information providing apparatus according to the present invention;
fig. 4 is a schematic structural diagram of an electronic device provided in the present invention.
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.
An embodiment of the present invention provides an information providing method, where an execution subject of the method may be a robot, and a flowchart of the information providing method is shown in fig. 1, and specifically includes:
s101: the method comprises the steps of collecting voice data of a user, and determining a target service scene from each preset service scene according to the voice data.
In the method provided by the embodiment of the invention, the robot collects the voice data of the user, the voice data is data containing the intention of the user, the service scene matched with the intention of the user is determined from each preset service scene according to the intention of the user contained in the voice data, and the determined service scene is determined as the target service scene.
The information providing method provided by the present invention can be applied to an airport robot.
S102: and acquiring a scene template of the target service scene.
In the method provided by the embodiment of the invention, the scene template of each service scene is pre-constructed, and optionally, the scene template and the scene name of the service scene have a corresponding relation.
And acquiring a scene template corresponding to the scene name according to the scene name of the target service scene, wherein the scene template comprises a required filling parameter list and a selected filling parameter list, and optionally, the required filling parameter list comprises a plurality of required filling parameters and the selected filling parameter list comprises a plurality of selected filling parameters.
Optionally, the opt-in and opt-out parameters in the opt-in and opt-out parameter list are used to further define the searched data items, for example, for the flight query service, each piece of flight information includes a plurality of attribute information, such as "departure date", "departure city", "arrival city", "price interval", "slot", "airline", "waypoint rate", "model", "stop or not", etc., where the "departure date", "departure city", "arrival city" and "arrival city" are all required to be specified in advance, therefore, the three attributes of "departure date", "departure city", "arrival city" are set as the mandatory parameters, and a large number of flights of different airlines and different types can be searched according to the three parameters, and each flight has different fare information according to different slots, therefore, the filling parameters need to be set to further limit the searched result so as to obtain the information that best meets the requirements of the user.
It should be noted that the required filling parameter and the optional filling parameter in each scene template are preset, and may also be changed according to actual requirements.
S103: and acquiring the necessary filling parameter information of each necessary filling parameter contained in the necessary filling parameter list.
In the method provided by the embodiment of the present invention, acquiring the necessary filling parameter information of each necessary filling parameter included in the necessary filling parameter list includes:
inquiring the user according to each necessary filling parameter in the necessary filling parameter list and a preset inquiry template corresponding to the necessary filling parameter;
and when response information corresponding to the inquiry responded by the user is received, extracting the necessary filling parameter information corresponding to the necessary filling parameters contained in the response information.
In the method provided by the embodiment of the invention, for each filling parameter in the filling parameter list, the user is queried according to the corresponding preset query template, and the filling parameter information of the filling parameter is extracted from the response information of the user responding to the query.
In the method provided by the embodiment of the invention, when the filling parameter information of the filling parameter is extracted from the response information of the user responding to the query, the acquisition of the filling parameter information can be completed by combining a knowledge base, a homothetic word and a knowledge reasoning mode.
For example, the acquisition of the mandatory fill parameter information is completed by combining a knowledge base: the airport A and the airport B refer to the same airport, the airport B is the alias of the airport A, but in a general navigation system, the airport A is often used for representation, if the airport B is included in the response information of a user, the airport B completes the reference disambiguation in a knowledge base according to the airport B, so that the airport A corresponding to the airport B is determined, and the airport A is the necessary parameter information; optionally, some static knowledge may also be obtained through a knowledge base, such as airport medical emergency services, security check services, transportation services, and the like.
For example, the following reasoning can be done for airport international security checkpoints: and deducing the name of the airport according to the name of the city where the user is located, and finally acquiring the international security inspection port information according to the name of the airport, so that the security inspection requirements such as the position, the need for security inspection and the like can be acquired according to the security inspection port information.
S104: and searching data items which accord with all necessary filling parameter information, and forming the searched data items into a first set.
In the method provided by the embodiment of the present invention, according to all the required filling parameters, each data item satisfying all the required filling parameters is searched, and a first set is formed according to each data item, where each required filling parameter is a constraint condition, and the data items searched through each constraint condition may include multiple data items, that is, the first set includes multiple data items.
S105: and judging whether the number of each data item in the first set is greater than a preset first threshold value.
In the method provided in the embodiment of the present invention, the number of data items included in the first set is obtained, the number is compared with a preset first threshold, and when the number is greater than the first threshold, it indicates that the number of the searched data items is too large, and in order to provide more accurate information for the user, the searched data items need to be further screened, and step S107 is executed; when the data amount is not greater than the first threshold, it indicates that the number of the searched data items meets the requirement, no further screening is needed, and step S106 is executed.
S106: the individual data items in the first set are provided to the user.
S107: and calculating the information gain ratio of each filling parameter in the filling parameter list, inquiring the user according to a preset inquiry template corresponding to the filling parameter with the largest information gain ratio, and acquiring filling parameter information contained in response information of the user responding to the inquiry.
In the method provided by the embodiment of the invention, the information gain ratio of each filling parameter in the filling parameter list is calculated, the filling parameter with the largest information gain ratio is determined from the information gain ratios according to the information gain ratios of the filling parameters, and a preset inquiry template corresponding to the filling parameter is obtained according to the determined filling parameter, wherein the obtained inquiry template is used for inquiring the current user, namely, the user is inquired according to the inquiry template, after the user receives the inquiry of the robot, the user responds to the inquiry, and when the robot receives the response information of the user responding to the inquiry, the filling parameter information corresponding to the filling parameter information is extracted from the response information. It should be noted that the specific process of extracting the padding information corresponding to the padding parameter from the response information of the user is similar to the above-mentioned specific process of extracting the required padding parameter information corresponding to the required padding parameter from the response information of the user, and is not described herein again.
Alternatively, the information gain ratio may be represented by the formula:
performing a calculation, wherein SplitInfoA(D) For selecting and filling the classification information, Gain, of the parameter A in the first set D foundA(D) To select and fill the information gain of the parameter a in the searched first set D, it should be noted that the calculation formula of the classification information and the information gain is the prior art, and is not described herein again.
S108: and deleting the data items which are not matched with the filling parameter information in the first set to obtain a new first set, and deleting the filling parameters with the largest information gain ratio in the filling parameter list to obtain a new filling parameter list.
In the method provided by the embodiment of the present invention, the data items in the first set that do not match the filling parameter information are deleted, that is, the data items that match the filling parameter information are determined from the first set, and the data items that do not match the filling parameter information are deleted, so as to obtain a new first set. For example, if the data items included in the current first set are a first data item, a second data item, a third data item and a fourth data item, the airline company in the first data item is a, the airline company in the second data item is B, the airline company in the third data item is C, and the airline company in the fourth data item is a, where the departure times of the first data item and the fourth data item are different, and the airline company a is extracted according to the response information of the user, the determined data items are the first data item and the fourth data item through screening, that is, the second data item and the third data item in the first set are deleted, and the new first set includes the first data item and the fourth data item.
In the method provided by the embodiment of the invention, the filling parameters with the largest information gain ratio in the filling parameter selecting list are deleted to obtain a new filling parameter selecting list, optionally, the obtained filling parameter selecting information can be refilled to the corresponding position of the filling parameter selecting list to mark that the filling parameters are used, and the information gain ratio of the filling parameters is not calculated in the subsequent calculation. And returns to step S105 to enable entry into the next cycle when the condition is satisfied.
It should be noted that, in the method provided in the embodiment of the present invention, interaction between the preset template corresponding to the required filling parameter and the user or interaction between the preset template corresponding to the selected filling parameter and the user may be queried in a plurality of output manners such as voice output, screen output, two-dimensional code output, emergency voice dialing, robot gesture, expression, location guidance, and the like, and the user may respond in a plurality of input manners such as natural voice, keyboard input, screen gesture, face image input, and id card input.
The information providing method provided by the embodiment of the invention comprises the steps of forming a first set by the searched data items which accord with all necessary filling parameter information, comparing the number of the data items in the first set with a preset first threshold value, if the number of the data items in the first set is larger than the preset first threshold value, calculating the information gain ratio of each filling parameter in a filling parameter list, selecting an inquiry template corresponding to the filling parameter with the largest information gain ratio to inquire a user so as to obtain filling parameter information corresponding to the filling parameter, deleting the data items which are not matched with the filling parameter information in the first set to obtain a new first set, deleting the filling parameter with the largest information gain ratio in the filling parameter list to obtain a new filling parameter list, comparing the number of the data items contained in the new first set with the first threshold value, the new first collection is provided to the user until the number of data items contained in the new first collection is not greater than the first threshold. By applying the information providing method provided by the embodiment of the invention, the filling parameters with the largest current information gain ratio are selected to inquire the user, namely, the user is inquired in a reasonable sequence of inquiring the filling parameters, the searching process is optimized, and the information required by the user is quickly and accurately determined, so that the interaction times with the user is reduced, and the service efficiency and the user experience are improved.
In the embodiment of the present invention described above, step S101 disclosed in fig. 1 determines a target service scenario from each preset service scenario according to the voice data, and a flowchart is shown in fig. 2, and includes the following steps:
s201: and recognizing the voice data to obtain voice characters corresponding to the voice data.
In the method provided by the embodiment of the invention, when the user proposes the user intention to the robot, the robot collects the voice data of the user, the voice data comprises data representing the user intention, and the collected voice data is identified so as to convert the voice data into voice characters.
S202: and performing word segmentation on the voice characters according to a preset word segmentation strategy to obtain word segmentation results of the voice characters.
In the method provided by the embodiment of the invention, the voice characters are segmented according to the preset segmentation strategy to obtain the segmentation result of the voice characters, optionally, stop words are removed in the segmentation process, the stop words can be defined in a stop word vocabulary in advance, and the stop words comprise some special symbols and some words which are not helpful or meaningless for service understanding, such as 'ground' and 'Do', and the like. Optionally, the word segmentation result may include a plurality of words, for example, the phonetic text is "i want to query city a to city B".
Optionally, an automaton AC tree is constructed for each vocabulary after the stop word is removed, so that the matching process of the predefined keyword vocabulary in the sentence can be accelerated.
Optionally, the preset word segmentation strategy is a chinese natural language processing method Hanlp, and the linguistic characters are segmented through a dictionary library provided by Hanlp, wherein the dictionary library includes professional vocabularies obtained by combining named entities in a related domain knowledge base.
S203: and acquiring the matching score of the word segmentation result and each preset service scene, and determining the matching score with the highest score.
In the method provided by the embodiment of the invention, a plurality of service scenes are preset, each service scene comprises at least one keyword, each vocabulary in the word segmentation result is matched with each keyword in the service scene aiming at each service scene, optionally, the matching process can be that each vocabulary in the word segmentation result is sequentially matched with each keyword in each service scene to obtain a plurality of matching scores of each vocabulary in the service scene, the highest score in the plurality of matching scores of each vocabulary is used as the target matching score of the vocabulary, the matching score of the word segmentation result and the service scene is determined according to the target matching score of each vocabulary in the word segmentation result, and the highest score is determined from each matching score after the matching score of the word segmentation result and each service scene is obtained.
S204: and judging whether the matching score with the highest score is larger than a preset matching threshold value.
In the method provided by the embodiment of the invention, after the matching scores of the word segmentation result and each service scene are obtained, the highest score is determined from each matching score, and the highest score is compared with the preset matching threshold value to determine the target service scene. If the highest score is greater than the matching threshold, step S205 is executed, and if the highest score is not greater than the matching threshold, step S206 is executed.
S205: and determining the service scene corresponding to the matching score with the highest score as a target service scene.
In the method provided by the embodiment of the invention, if the highest score is greater than the matching threshold, the service scene corresponding to the highest score is determined as the target service scene, wherein the highest score refers to the matching score with the highest score in the matching scores.
S206: and inputting each vocabulary in the word segmentation result into a pre-constructed word vector model to obtain a word vector of each vocabulary.
In the method provided by the embodiment of the invention, a word vector model is constructed in advance, each vocabulary in the word segmentation result is input into the word vector model, and the word vector of each vocabulary is output after the word vector model is processed.
Optionally, the training data of the word vector model can be derived from a corpus, and the word vector model is trained based on the training data in the corpus, wherein, for the aviation field, the data in the corpus covers encyclopedia, Wikipedia, and combines to crawl rich data of news data in the aviation field.
S207: and determining the similarity with each service scene, and comparing the similarity with the maximum value with a preset similarity threshold.
In the method provided by the embodiment of the invention, each word vector in each word segmentation result is subjected to normalization processing to obtain a normalized word vector of each word, for each service scene, similarity calculation is performed on each normalized word vector and the word vector of each keyword corresponding to the service scene to obtain the similarity between each normalized word vector and the word vector of each keyword in the service scene, namely, a plurality of similarities of each normalized word vector are obtained, for each normalized word vector, the similarity with the largest value is taken as the target similarity of the normalized word vector, and the similarity with the service is determined according to the target similarity of each normalized word vector. Alternatively, the similarity calculation may be performed using cosine similarity.
And determining the similarity with the maximum value from the similarities corresponding to the service scenes, and comparing the similarity with the maximum value with a preset similarity threshold.
S208: and if the similarity with the maximum value is greater than the similarity threshold, determining the service scene corresponding to the similarity with the maximum value as a target service scene.
In the method provided by the embodiment of the invention, if the similarity with the largest numerical value is greater than the similarity threshold, the service scene corresponding to the similarity with the largest numerical value is determined as the target service scene. And if the similarity with the maximum numerical value is not greater than the similarity threshold, turning to a QA dialogue, namely a scene of constant chatting, carrying out similarity calculation on the sentence and Q, namely question sentences in a QA library, matching the sentence with the closest question sentence, and then answering the answer sentence corresponding to the question sentence. If the process of matching the question fails, a general answer is passed. The general answer has a list of answers from which a random answer is drawn to ask the user for a question, such as "how well did small K understand you, can you change for an expression? ".
In the information providing method provided by the embodiment of the invention, voice data of a user is identified to obtain voice words, the voice words are segmented according to a preset segmentation strategy, the segmented result is matched with the preset keywords of each service scene, if the matching fails, the word vector of each word after the segmentation is normalized, the similarity of each word vector after the normalization and the word vector of the keywords in each service scene is calculated, and when the similarity with the largest value is greater than a preset similarity threshold value, the service model corresponding to the similarity with the largest value is determined as the target service model.
The above embodiment of the present invention, after step S106 disclosed in fig. 1 provides each data item in the first set to the user, further includes the following steps:
acquiring the preference of the user and historical data corresponding to the target service scene;
and providing services to the user according to the historical data and the preference of the user.
According to the method provided by the embodiment of the invention, the preference of the user and the historical data corresponding to the target service scene are obtained, and the behavior of the user is actively inquired, reminded and suggested according to the preference and the historical data of the user. For example, after the check-in is finished, the robot can provide suggestions for whether to perform security check on the user according to the current security check opening and closing time of the flight where the current user is located and the current security check congestion state; under the condition of long distance, a rest or dining scheme is actively recommended to the user according to the position and the time period of the user and the consumption habits of the user in combination with the similar characteristics. The whole service process of the robot is more humanized.
The above mentioned active queries, reminders and suggestions of user behavior are exemplified as follows:
the bot may actively initiate a personalized content query to the user. Such as setting boarding time incoming call reminder.
The user: asking for the scheduled departure time of a flight with a flight number XXXX?
The robot comprises: the planned departure time for a flight with a flight number XXXX is 10, 20 points.
The robot comprises: 30 minutes from the latest boarding time, a flight with a flight number XXXX will be at 11: and finishing boarding for 50, F1-X to F3-Y, wherein the shortest walking time is about 20 minutes. And advising people to board the airplane by taking a battery car and going to an F3-y boarding gate.
Scene 2:
the robot comprises: there are 2 hours 30 minutes from the latest boarding time, and a flight with a flight number XXXX will be 1: and 50, finishing boarding, setting a boarding reminder, informing a letter on time, providing service facilities such as catering, leisure entertainment and the like for the person at the airport, and asking a small K for what the person wants to eat and want to play.
Corresponding to the method described in fig. 1, an embodiment of the present invention further provides an information providing apparatus, which is used for implementing the method in fig. 1 specifically, and a schematic structural diagram of the information providing apparatus is shown in fig. 3, and specifically includes:
the acquisition unit 301 is configured to acquire voice data of a user and determine a target service scene from each preset service scene according to the voice data;
a first obtaining unit 302, configured to obtain a scene template of the target service scene; the scene template comprises a mandatory filling parameter list and a selective filling parameter list;
a second obtaining unit 303, configured to obtain the necessary padding parameter information of each necessary padding parameter included in the necessary padding parameter list;
a searching unit 304, configured to search for data items that meet all the filling parameter information, and combine the searched data items into a first set;
a determining unit 305, configured to determine whether the number of each data item in the first set is greater than a preset first threshold;
a first calculating unit 306, configured to calculate an information gain ratio of each padding parameter in the padding parameter list when the number of each data item in the first set is greater than the first threshold, and query the user according to a preset query template corresponding to the padding parameter with the largest information gain ratio;
a deleting unit 307, configured to, when response information that the user responds to the query is received, obtain filling parameter information in the response information, delete a data item in the first set that does not match the filling parameter information, obtain a new first set, and delete a filling parameter with a largest information gain ratio in the filling parameter list, so as to obtain a new filling parameter list;
a second calculating unit 308, configured to re-determine, based on the new first set and the new padding parameter list, whether the number of each data item in the new first set is greater than the first threshold, and when the number of each data item in the new first set is greater than the first threshold, calculate an information gain ratio of each padding parameter in the new padding parameter list until the finally determined number of each data item in the new first set is not greater than the first threshold;
a first providing unit 309, configured to provide each data item in the finally determined new first set to the user.
The information providing device provided by the embodiment of the invention combines the searched data items which accord with all necessary filling parameter information into a first set, compares the number of the data items in the first set with a preset first threshold value, calculates the information gain ratio of each filling parameter in a filling parameter list if the number of the data items in the first set is larger than the preset first threshold value, selects the query template corresponding to the filling parameter with the largest information gain ratio to query the user so as to obtain filling parameter information corresponding to the filling parameter, deletes the data items which are not matched with the filling parameter information in the first set to obtain a new first set, deletes the filling parameter with the largest information gain ratio in the filling parameter list to obtain a new filling parameter list, compares the number of the data items contained in the new first set with the first threshold value, the new first collection is provided to the user until the number of data items contained in the new first collection is not greater than the first threshold. By applying the information providing device provided by the embodiment of the invention, the filling parameters with the largest current information gain ratio are selected to inquire the user, namely, the user is inquired in a reasonable sequence of inquiring the filling parameters, the searching process is optimized, and the information required by the user is quickly and accurately determined, so that the interaction times with the user is reduced, and the service efficiency and the user experience are improved.
In an embodiment of the present invention, based on the foregoing scheme, the acquisition unit 301 is configured to:
the recognition subunit is used for recognizing the voice data and obtaining voice characters corresponding to the voice data;
the word segmentation subunit is used for segmenting the voice characters according to a preset word segmentation strategy to obtain word segmentation results of the voice characters; the word segmentation result comprises a plurality of words;
the first acquiring subunit is used for acquiring each preset service scene;
the matching subunit is used for matching each vocabulary in the word segmentation result with each keyword corresponding to the service scene aiming at each service scene to obtain a matching score corresponding to the service scene;
the first comparison subunit is used for determining the matching score with the highest score and comparing the matching score with the highest score with a preset matching threshold;
and the first determining subunit is configured to determine, if the matching score with the highest score is greater than the matching threshold, the service scenario corresponding to the matching score with the highest score as the target service scenario.
In an embodiment of the present invention, based on the foregoing scheme, the acquisition unit 301 is configured to:
the input subunit is configured to, if the matching score with the highest score is not greater than the matching threshold, input each vocabulary in the word segmentation result into a pre-constructed word vector model to obtain a word vector of each vocabulary;
the normalization subunit is used for performing normalization processing on the word vector of each vocabulary to obtain a normalized word vector of each vocabulary;
the calculation subunit is configured to, for each service scene, perform similarity calculation on each normalized word vector and the word vector of each keyword corresponding to the service scene to obtain a similarity corresponding to the service scene;
the second comparison subunit is used for determining the similarity with the maximum numerical value and comparing the similarity with a preset similarity threshold value;
and a second determining subunit, configured to determine, if the similarity with the largest value is greater than the similarity threshold, the service scene corresponding to the similarity with the largest value as a target service scene.
In an embodiment of the present invention, based on the foregoing solution, the second obtaining unit 303 is configured to:
the inquiry subunit is configured to inquire the user according to a preset inquiry template corresponding to the mandatory fill parameter for each mandatory fill parameter in the mandatory fill parameter list;
and the second acquisition subunit is used for acquiring the necessary filling parameter information in the response information when receiving the response information of the user responding to the inquiry.
In an embodiment of the present invention, based on the foregoing solution, the method is further configured to:
a third obtaining unit, configured to obtain a preference of the user and historical data corresponding to the target service scenario;
and the second providing unit is used for providing services for the user according to the historical data and the preference of the user.
The embodiment of the invention also provides a storage medium, which comprises a stored instruction, wherein when the instruction runs, the device where the storage medium is located is controlled to execute the information providing method.
An electronic device is provided in an embodiment of the present invention, and the structural diagram of the electronic device is shown in fig. 4, which specifically includes a memory 401 and one or more instructions 402, where the one or more instructions 402 are stored in the memory 401 and configured to be executed by one or more processors 403 to perform the following operations for executing the one or more instructions 402:
collecting voice data of a user, and determining a target service scene from each preset service scene according to the voice data;
acquiring a scene template of the target service scene; the scene template comprises a mandatory filling parameter list and a selective filling parameter list;
acquiring necessary filling parameter information of each necessary filling parameter contained in the necessary filling parameter list;
searching data items which accord with all the filling parameter information, and forming a first set by the searched data items;
judging whether the number of each data item in the first set is greater than a preset first threshold value or not;
when the number of each data item in the first set is larger than the first threshold value, calculating an information gain ratio of each filling parameter in the filling parameter list, and inquiring the user according to a preset inquiry template corresponding to the filling parameter with the largest information gain ratio;
when response information of the user responding to the inquiry is received, acquiring filling parameter information in the response information, deleting data items which are not matched with the filling parameter information in the first set to obtain a new first set, and deleting filling parameters with the largest information gain ratio in the filling parameter list to obtain a new filling parameter list;
whether the number of each data item in the new first set is larger than the first threshold value or not is judged again on the basis of the new first set and the new filling parameter list, and when the number of each data item in the new first set is larger than the first threshold value, the information gain ratio of each filling parameter in the new filling parameter list is calculated until the finally determined number of each data item in the new first set is not larger than the first threshold value;
and providing each data item in the finally determined new first set to the user.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. For the device-like embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the units may be implemented in the same software and/or hardware or in a plurality of software and/or hardware when implementing the invention.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The above detailed description is provided for an information providing method and apparatus, and the principle and the implementation of the present invention are explained by applying specific examples, and the description of the above examples is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. An information providing method, comprising:
collecting voice data of a user, and determining a target service scene from each preset service scene according to the voice data;
acquiring a scene template of the target service scene; the scene template comprises a mandatory filling parameter list and a selective filling parameter list;
acquiring necessary filling parameter information of each necessary filling parameter contained in the necessary filling parameter list;
searching data items which accord with all the filling parameter information, and forming a first set by the searched data items;
judging whether the number of each data item in the first set is greater than a preset first threshold value or not;
when the number of each data item in the first set is larger than the first threshold value, calculating an information gain ratio of each filling parameter in the filling parameter list, and inquiring the user according to a preset inquiry template corresponding to the filling parameter with the largest information gain ratio;
when response information of the user responding to the inquiry is received, acquiring filling parameter information in the response information, deleting data items which are not matched with the filling parameter information in the first set to obtain a new first set, and deleting filling parameters with the largest information gain ratio in the filling parameter list to obtain a new filling parameter list;
whether the number of each data item in the new first set is larger than the first threshold value or not is judged again on the basis of the new first set and the new filling parameter list, and when the number of each data item in the new first set is larger than the first threshold value, the information gain ratio of each filling parameter in the new filling parameter list is calculated until the finally determined number of each data item in the new first set is not larger than the first threshold value;
and providing each data item in the finally determined new first set to the user.
2. The method of claim 1, wherein the determining a target service scenario from among preset service scenarios according to the voice data comprises:
recognizing the voice data to obtain voice characters corresponding to the voice data;
performing word segmentation on the voice characters according to a preset word segmentation strategy to obtain word segmentation results of the voice characters; the word segmentation result comprises a plurality of words;
acquiring each preset service scene;
for each service scene, matching each vocabulary in the word segmentation result with each keyword corresponding to the service scene to obtain a matching score corresponding to the service scene;
determining the matching score with the highest score, and comparing the matching score with the highest score with a preset matching threshold;
and if the matching score with the highest score is larger than the matching threshold, determining the service scene corresponding to the matching score with the highest score as a target service scene.
3. The method of claim 2, further comprising:
if the matching score with the highest score is not larger than the matching threshold, inputting each vocabulary in the word segmentation result into a pre-constructed word vector model to obtain a word vector of each vocabulary;
carrying out normalization processing on the word vector of each vocabulary to obtain a normalized word vector of each vocabulary;
for each service scene, performing similarity calculation on each normalized word vector and the word vector of each keyword corresponding to the service scene to obtain similarity corresponding to the service scene;
determining the similarity with the maximum value, and comparing the similarity with the maximum value with a preset similarity threshold;
and if the similarity with the maximum value is greater than the similarity threshold, determining the service scene corresponding to the similarity with the maximum value as a target service scene.
4. The method according to claim 1, wherein said obtaining the padding parameter information of each padding parameter included in the padding parameter list comprises:
inquiring the user according to each necessary filling parameter in the necessary filling parameter list and a preset inquiry template corresponding to the necessary filling parameter;
and when response information of the user responding to the inquiry is received, acquiring the necessary filling parameter information in the response information.
5. The method of claim 1, wherein after providing the first set to the user, further comprising:
acquiring the preference of the user and historical data corresponding to the target service scene;
and providing services to the user according to the historical data and the preference of the user.
6. An information providing apparatus, comprising:
the system comprises a collecting unit, a processing unit and a processing unit, wherein the collecting unit is used for collecting voice data of a user and determining a target service scene from each preset service scene according to the voice data;
a first obtaining unit, configured to obtain a scene template of the target service scene; the scene template comprises a mandatory filling parameter list and a selective filling parameter list;
a second obtaining unit, configured to obtain the necessary padding parameter information of each necessary padding parameter included in the necessary padding parameter list;
the searching unit is used for searching the data items which accord with all the necessary filling parameter information and forming a first set by the searched data items;
the judging unit is used for judging whether the number of each data item in the first set is greater than a preset first threshold value or not;
the first calculating unit is used for calculating the information gain ratio of each filling parameter in the filling parameter list when the number of each data item in the first set is larger than the first threshold value, and inquiring the user according to a preset inquiry template corresponding to the filling parameter with the largest information gain ratio;
a deleting unit, configured to, when response information that the user responds to the query is received, obtain filling parameter information in the response information, delete a data item in the first set that does not match the filling parameter information, obtain a new first set, delete a filling parameter with a largest information gain ratio in the filling parameter list, and obtain a new filling parameter list;
a second calculating unit, configured to re-determine, based on the new first set and the new padding parameter list, whether the number of each data item in the new first set is greater than the first threshold, and when the number of each data item in the new first set is greater than the first threshold, calculate an information gain ratio of each padding parameter in the new padding parameter list until the finally determined number of each data item in the new first set is not greater than the first threshold;
a first providing unit, configured to provide each data item in the finally determined new first set to the user.
7. The apparatus of claim 6, wherein the acquisition unit comprises:
the recognition subunit is used for recognizing the voice data and obtaining voice characters corresponding to the voice data;
the word segmentation subunit is used for segmenting the voice characters according to a preset word segmentation strategy to obtain word segmentation results of the voice characters; the word segmentation result comprises a plurality of words;
the first acquiring subunit is used for acquiring each preset service scene;
the matching subunit is used for matching each vocabulary in the word segmentation result with each keyword corresponding to the service scene aiming at each service scene to obtain a matching score corresponding to the service scene;
the first comparison subunit is used for determining the matching score with the highest score and comparing the matching score with the highest score with a preset matching threshold;
and the first determining subunit is configured to determine, if the matching score with the highest score is greater than the matching threshold, the service scenario corresponding to the matching score with the highest score as the target service scenario.
8. The apparatus of claim 7, wherein the acquisition unit comprises:
the input subunit is configured to, if the matching score with the highest score is not greater than the matching threshold, input each vocabulary in the word segmentation result into a pre-constructed word vector model to obtain a word vector of each vocabulary;
the normalization subunit is used for performing normalization processing on the word vector of each vocabulary to obtain a normalized word vector of each vocabulary;
the calculation subunit is configured to, for each service scene, perform similarity calculation on each normalized word vector and the word vector of each keyword corresponding to the service scene to obtain a similarity corresponding to the service scene;
the second comparison subunit is used for determining the similarity with the maximum numerical value and comparing the similarity with a preset similarity threshold value;
and a second determining subunit, configured to determine, if the similarity with the largest value is greater than the similarity threshold, the service scene corresponding to the similarity with the largest value as a target service scene.
9. The apparatus of claim 6, wherein the second obtaining unit comprises:
the inquiry subunit is configured to inquire the user according to a preset inquiry template corresponding to the mandatory fill parameter for each mandatory fill parameter in the mandatory fill parameter list;
and the second acquisition subunit is used for acquiring the necessary filling parameter information in the response information when receiving the response information of the user responding to the inquiry.
10. The apparatus of claim 6, further comprising:
a third obtaining unit, configured to obtain a preference of the user and historical data corresponding to the target service scenario;
and the second providing unit is used for providing services for the user according to the historical data and the preference of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910962487.4A CN110727773B (en) | 2019-10-11 | 2019-10-11 | Information providing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910962487.4A CN110727773B (en) | 2019-10-11 | 2019-10-11 | Information providing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110727773A CN110727773A (en) | 2020-01-24 |
| CN110727773B true CN110727773B (en) | 2022-02-01 |
Family
ID=69220908
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910962487.4A Active CN110727773B (en) | 2019-10-11 | 2019-10-11 | Information providing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110727773B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114520928B (en) * | 2020-11-18 | 2024-01-26 | 北京字跳网络技术有限公司 | Display information generation method, information display device and electronic equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081631A (en) * | 2009-11-30 | 2011-06-01 | 国际商业机器公司 | Answer support system and method |
| JP2015069608A (en) * | 2013-10-01 | 2015-04-13 | Kddi株式会社 | Program for progressing search interactively with user, server, and method |
| CN107169034A (en) * | 2017-04-19 | 2017-09-15 | 畅捷通信息技术股份有限公司 | A kind of method and system of many wheel man-machine interactions |
| CN107958091A (en) * | 2017-12-28 | 2018-04-24 | 北京贝塔智投科技有限公司 | A kind of NLP artificial intelligence approaches and interactive system based on financial vertical knowledge mapping |
| CN108009287A (en) * | 2017-12-25 | 2018-05-08 | 北京中关村科金技术有限公司 | A kind of answer data creation method and relevant apparatus based on conversational system |
| CN109192300A (en) * | 2018-08-17 | 2019-01-11 | 百度在线网络技术（北京）有限公司 | Intelligent way of inquisition, system, computer equipment and storage medium |
| CN109658928A (en) * | 2018-12-06 | 2019-04-19 | 山东大学 | A kind of home-services robot cloud multi-modal dialog method, apparatus and system |
| CN109739965A (en) * | 2018-12-29 | 2019-05-10 | 深圳前海微众银行股份有限公司 | Moving method and device, equipment, the readable storage medium storing program for executing of cross-cutting dialog strategy |
| CN110008327A (en) * | 2019-04-01 | 2019-07-12 | 河北省讯飞人工智能研究院 | Law answers generation method and device |
| CN110162602A (en) * | 2019-05-31 | 2019-08-23 | 浙江核新同花顺网络信息股份有限公司 | A kind of intelligent interactive method and system |
-
2019
- 2019-10-11 CN CN201910962487.4A patent/CN110727773B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081631A (en) * | 2009-11-30 | 2011-06-01 | 国际商业机器公司 | Answer support system and method |
| JP2015069608A (en) * | 2013-10-01 | 2015-04-13 | Kddi株式会社 | Program for progressing search interactively with user, server, and method |
| CN107169034A (en) * | 2017-04-19 | 2017-09-15 | 畅捷通信息技术股份有限公司 | A kind of method and system of many wheel man-machine interactions |
| CN108009287A (en) * | 2017-12-25 | 2018-05-08 | 北京中关村科金技术有限公司 | A kind of answer data creation method and relevant apparatus based on conversational system |
| CN107958091A (en) * | 2017-12-28 | 2018-04-24 | 北京贝塔智投科技有限公司 | A kind of NLP artificial intelligence approaches and interactive system based on financial vertical knowledge mapping |
| CN109192300A (en) * | 2018-08-17 | 2019-01-11 | 百度在线网络技术（北京）有限公司 | Intelligent way of inquisition, system, computer equipment and storage medium |
| CN109658928A (en) * | 2018-12-06 | 2019-04-19 | 山东大学 | A kind of home-services robot cloud multi-modal dialog method, apparatus and system |
| CN109739965A (en) * | 2018-12-29 | 2019-05-10 | 深圳前海微众银行股份有限公司 | Moving method and device, equipment, the readable storage medium storing program for executing of cross-cutting dialog strategy |
| CN110008327A (en) * | 2019-04-01 | 2019-07-12 | 河北省讯飞人工智能研究院 | Law answers generation method and device |
| CN110162602A (en) * | 2019-05-31 | 2019-08-23 | 浙江核新同花顺网络信息股份有限公司 | A kind of intelligent interactive method and system |
Non-Patent Citations (1)
| Title |
|---|
| 问答系统中特征提取方法研究;易小凯;《电脑知识与技术》;20180505;第14卷(第13期);171-172 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110727773A (en) | 2020-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10719507B2 (en) | System and method for natural language processing | |
| CN110222160B (en) | Intelligent semantic document recommendation method and device and computer readable storage medium | |
| CN107943998B (en) | Man-machine conversation control system and method based on knowledge graph | |
| CN110301117B (en) | Method and apparatus for providing response in session | |
| US11693894B2 (en) | Conversation oriented machine-user interaction | |
| CN106649742B (en) | Database maintenance method and device | |
| CN109918650B (en) | Interview intelligent robot device capable of automatically generating interview draft and intelligent interview method | |
| US20190370398A1 (en) | Method and apparatus for searching historical data | |
| US20160092434A1 (en) | Integrated word n-gram and class m-gram language models | |
| US20140309990A1 (en) | Semantic re-ranking of nlu results in conversational dialogue applications | |
| CN105354199B (en) | A kind of recognition methods of entity meaning and system based on scene information | |
| CN109410927A (en) | Offline order word parses the audio recognition method combined, device and system with cloud | |
| CN110675871B (en) | Voice recognition method and device | |
| CN110096567A (en) | Selection method, system are replied in more wheels dialogue based on QA Analysis of Knowledge Bases Reasoning | |
| US11410643B2 (en) | Response generation for conversational computing interface | |
| WO2014175921A1 (en) | Systems and methods for providing metadata-dependent language models | |
| CN106446018B (en) | Query information processing method and device based on artificial intelligence | |
| CN110473543B (en) | Voice recognition method and device | |
| Adel et al. | Features for factored language models for code-Switching speech. | |
| KR101677859B1 (en) | Method for generating system response using knowledgy base and apparatus for performing the method | |
| CN111199149B (en) | Sentence intelligent clarification method and system for dialogue system | |
| CN112183075B (en) | Method and device for extracting slots in conversation, electronic equipment and storage medium | |
| CN109739965A (en) | Moving method and device, equipment, the readable storage medium storing program for executing of cross-cutting dialog strategy | |
| CN106951433B (en) | Retrieval method and device | |
| CN111914157A (en) | Travel scheme generation method and system based on user preference |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |