CN111259209A - User intention prediction method based on artificial intelligence, electronic device and storage medium - Google Patents

Abstract

The invention relates to the technical field of data processing, and provides a user intention prediction method based on artificial intelligence, an electronic device and a computer storage medium, wherein the method comprises the following steps: receiving a query sentence input by a user, analyzing a plurality of keywords, inputting a pre-trained recognition model, extracting semantic features corresponding to the keywords, and counting the number of the keywords; when the number of the keywords of the intention semantic features is zero, predicting the intention of the query statement according to conditions, dimensions, a calculation method and the number of the keywords corresponding to the measured semantic features according to a preset matching rule, and finally, correcting the query statement according to the predicted intention to retrieve to obtain target data and generate an expected graph and a data table corresponding to the query statement. According to the method and the device, the query intention of the user is analyzed and predicted according to the query sentence input by the user for retrieval, the retrieved data is obtained and displayed to the user according to different graphic functions, the displayed graphics are ensured to meet the requirements of the user, and the experience degree of the user is further improved.

Description

User intention prediction method based on artificial intelligence, electronic device and storage medium

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a user intention prediction method based on artificial intelligence, an electronic device, and a computer-readable storage medium.

Background

Many existing software have data query functions based on natural language. To help users better analyze data from multiple angles, the software presents the data from queries to users through data tables in different graphical functions, such as line charts, bar charts, pie charts, etc. And outputting the corresponding data table of the graphic display by different query sentences input by the user.

However, the user has the following disadvantages in the process of using software to query:

1. before a user inputs a query statement, the user needs to clearly determine which graphic display effect is wanted in advance, and the graphic display requirement wanted by the user is often unclear;

2. for the natural language input by the user, the software cannot be correctly analyzed, so that the displayed graph may not meet the requirements of the user.

Therefore, a system and method for analyzing and predicting the query intent of a user is needed.

Disclosure of Invention

In view of the above, the present invention provides a user intention prediction method based on artificial intelligence, an electronic device and a computer-readable storage medium, and the main purpose of the present invention is to analyze and predict the query intention of a user according to a query sentence input by the user to perform a search, obtain search data and display the search data to the user according to different graphic functions, so as to ensure that the displayed graphic meets the user requirements and further improve the user experience.

In order to achieve the above object, the present invention provides a method for predicting user intention based on artificial intelligence, applied to an electronic device, the method comprising:

a receiving step: receiving a query sentence input by a user through a terminal, analyzing the query sentence and extracting a plurality of keywords;

a statistical step: inputting the keywords into a pre-trained recognition model, extracting semantic features corresponding to the keywords, and counting the number of the keywords contained in each semantic feature, wherein the semantic features comprise conditions, dimensions, a calculation method, measurement and intention;

a prediction step: when the number of the keywords contained in the counted intention semantic features is zero, judging that the intention of the query statement input by a user is ambiguous, predicting the intention of the query statement according to the counted conditions, dimensions, a calculation method and the number of the keywords contained in the semantic features measured according to a preset matching rule, wherein each predicted intention corresponds to an expected graph;

a generation step: and correcting the query statement according to the predicted intention, performing data retrieval on a database to obtain target data, and generating an expected graph corresponding to the query statement and a data table contained in the expected graph according to the target data.

In addition, to achieve the above object, the present invention further provides an electronic device, which includes a memory and a processor, wherein the memory stores an intention query program operable on the processor, and the intention query program, when executed by the processor, implements the following steps:

a receiving step: receiving a query sentence input by a user through a terminal, analyzing the query sentence and extracting a plurality of keywords;

a statistical step: inputting the keywords into a pre-trained recognition model, extracting semantic features corresponding to the keywords, and counting the number of the keywords contained in each semantic feature, wherein the semantic features comprise conditions, dimensions, a calculation method, measurement and intention;

a prediction step: when the number of the keywords contained in the counted intention semantic features is zero, judging that the intention of the query statement input by a user is ambiguous, predicting the intention of the query statement according to the statistical conditions, dimensions, a calculation method and the number of the keywords contained in the semantic features measured according to a preset matching rule, wherein each predicted intention corresponds to an expected graph;

a generation step: and correcting the query statement according to the predicted intention, performing data retrieval on a database to obtain target data, and generating an expected graph corresponding to the query statement and a data table contained in the expected graph according to the target data.

In addition, to achieve the above object, the present invention also provides a computer readable storage medium, which includes an intention query program, and when the intention query program is executed by a processor, the intention query program can implement any one of the steps of the artificial intelligence based user intention prediction method as described above

The invention provides an artificial intelligence-based user intention prediction method, an electronic device and a computer-readable storage medium, which are characterized in that a plurality of keywords are analyzed by receiving query sentences input by a user, the keywords are input into a pre-trained recognition model to extract semantic features corresponding to the keywords, and the number of the keywords correspondingly contained in the semantic features of conditions, dimensions, a calculation method, measurement and intention is counted; and when the number of the keywords of the intention semantic features is zero, predicting the intention of the query statement according to the number of the keywords correspondingly contained in other statistical semantic features and a preset matching rule, finally correcting the query statement according to the predicted intention, retrieving target data in a database, and generating an expected graph corresponding to the query statement and a data table contained in the expected graph. According to the method and the device, the query intention of the user is analyzed and predicted according to the query sentence input by the user for retrieval, the retrieved data is obtained and displayed to the user according to different graphic functions, the displayed graphics are ensured to meet the requirements of the user, and the experience degree of the user is further improved.

Drawings

FIG. 1 is a diagram of an electronic device according to a preferred embodiment of the present invention;

FIG. 2 is a block diagram of a preferred embodiment of the intent query routine of FIG. 1;

FIG. 3 is a flowchart illustrating a method for predicting user intent based on artificial intelligence according to a preferred embodiment of the present invention;

the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention 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 invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the description relating to "first", "second", etc. in the present invention is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.

Referring to fig. 1, a schematic diagram of an electronic device according to a preferred embodiment of the invention is shown. The electronic apparatus 1 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a command set or stored in advance. The electronic device 1 may be a computer, or may be a single network server, a server group composed of a plurality of network servers, or a cloud composed of a large number of hosts or network servers based on cloud computing, where cloud computing is one of distributed computing and is a super virtual computer composed of a group of loosely coupled computers.

In the present embodiment, the electronic device 1 may include, but is not limited to, a memory 11, a processor 12, and a display 13, which may be communicatively connected to each other through a system bus, and the memory 11 stores an intention query program 10 that may be executed on the processor 12. It is noted that fig. 1 only shows the electronic device 1 with components 11-13, but it is to be understood that not all shown components are required to be implemented, and that more or less components may be implemented instead.

The storage 11 includes a memory and at least one type of readable storage medium. The memory provides cache for the operation of the electronic device 1; the readable storage medium may be a non-volatile storage medium such as flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the readable storage medium may be an internal storage unit of the electronic apparatus 1, such as a hard disk of the electronic apparatus 1; in other embodiments, the non-volatile storage medium may also be an external storage device of the electronic apparatus 1, such as a plug-in hard disk provided on the electronic apparatus 1, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. In this embodiment, the readable storage medium of the memory 11 is generally used for storing an operating system and various application software installed in the electronic device 1, such as the intention query program 10 in an embodiment of the present invention. Further, the memory 11 may also be used to temporarily store various types of data that have been output or are to be output.

The processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 12 is generally used for controlling the overall operation of the electronic apparatus 1, such as performing control and processing related to data interaction or communication with the other devices. In this embodiment, the processor 12 is configured to run the program code stored in the memory 11 or process data, such as running the intention query program 10.

The intent query program 10 is stored in memory 11 and includes computer readable instructions stored in memory 11 that are executable by processor 12 to implement the methods of the embodiments of the present application.

In one embodiment, the above-mentioned intent query program 10, when executed by the processor 12, implements the following steps:

a receiving step: receiving a query sentence input by a user through a terminal, and analyzing the query sentence to extract a plurality of keywords.

For example, in one embodiment, a user inputs a query sentence of "Shanghai male career distribution" through a terminal (such as a computer, a mobile phone or an application APP), identifies and analyzes sentence components of the query sentence, analyzes keywords (such as keywords: Shanghai, male, career and distribution) of the query sentence, and extracts the keywords.

A statistical step: inputting the keywords into a pre-trained recognition model, extracting semantic features corresponding to the keywords, and counting the number of the keywords contained in each semantic feature, wherein the semantic features comprise conditions, dimensions, a calculation method, measurement and intention.

In this implementation, the semantic features of conditions, dimensions, calculation methods, measures and intentions corresponding to the keywords are extracted through the recognition model, and the number of the included keywords of each semantic feature is counted.

The conditional semantic features are denoted by f (filter), and refer to keywords as data filtering or filtering, such as "shanghai", "male";

the dimension semantic features are denoted by d (dimension), which refers to the dimension in which the final graphic presentation specifically presents the keywords, such as "occupation";

the computational method semantic features are denoted m (method), referring to keywords for the computation of metrics, such as "average";

the metric semantic features are expressed by m (measure), and refer to a keyword as a statistical object, such as "age";

the intention semantic feature is denoted by i (intent), and refers to a graphical presentation result that the user desires to obtain, such as "distribution".

Further, the pre-trained recognition model comprises:

acquiring a keyword;

classifying preset semantic features according to the field attributes of the keywords, wherein the semantic features comprise conditions, dimensions, a calculation method, measurement and intentions;

and training an identification model based on the keywords contained in each semantic feature obtained by classification to obtain the semantic features corresponding to the keywords, and finishing the training of the identification model.

Specifically, the recognition model is a deep learning model, and can perform semantic understanding according to field attributes of the trained keywords and recognize semantic features corresponding to the keywords, wherein the semantic features include conditions, dimensions, a calculation method, measurement and intention. When a plurality of keywords are extracted from the query sentence input by the user, the semantic features corresponding to each keyword can be identified through the identification model.

For example, in one embodiment, the query sentence input by the user is "shanghai male different occupational average age distribution", the extracted keywords are "shanghai", "male", "occupational", "average", "age" and "distribution", and the conditional semantic features obtained by using the recognition model are "shanghai", "male"; the dimension semantic features are "profession"; the semantic features of the calculation method are 'average'; the metric semantic feature is "age"; the intent semantic feature is "distribution".

A prediction step: and when the number of the keywords contained in the counted intention semantic features is zero, judging that the intention of the query statement input by the user is ambiguous, predicting the intention of the query statement according to the counted conditions, dimensions, calculation methods and the number of the keywords contained in the semantic features measured according to a preset matching rule, wherein each predicted intention corresponds to an expected graph.

When the intent of the query statement is ambiguous, it is difficult for the system to give a correct graphical presentation. In order to overcome this difficulty, the present embodiment predicts the intention of the query statement according to a preset matching rule by using the counted number of keywords included in correspondence to the semantic features of the conditions, dimensions, calculation methods, and metrics, so as to perform intention completion on the query statement with an ambiguous intention input by the user.

In this embodiment, a type of expected pattern is preset for each predicted intention. The keywords of the intention comprise counts, distribution, proportion, comparison, primary distribution and secondary distribution and correlation, the expected graphs comprise a count graph, a histogram, a pie graph, a two-column histogram, a horizontal histogram and a polymerization histogram, and each keyword of the intention corresponds to each expected graph respectively. For example,

a. if the keyword of the intention of the query sentence of 'how many people are in Shanghai male' is the count, the corresponding expected graph is displayed by a digital graph;

b. if the keywords of the intention of the query statement of 'Shanghai male occupation distribution' are distributed, the corresponding expected graph is displayed by a histogram;

c. if the keyword of the intention that the query statement is 'Shanghai male unmarried proportion' is a proportion, the corresponding expected graph is displayed in a pie chart;

d. if the keyword of the intention of the query statement of 'income comparison between men and women' is comparison, the corresponding expected graph is displayed in two columns of bar graphs;

e. the keywords of the intention of the query sentence which is 'what the first ten jobs with higher average income are' are distributed primarily and secondarily, and the corresponding expected graph is displayed by a horizontal histogram;

f. the query statement is "how relevant are careers and academic records? "the intended keyword is a relevance, the corresponding expected graph is shown as an aggregate histogram.

Further, the preset matching rule further includes:

classifying intention condition combinations corresponding to each expected graph according to the expected graphs, wherein each intention condition combination is composed of one or more of conditions, dimensions, calculation methods and measured semantic features;

according to the pre-counted conditions, dimensions, a calculation method and the number of keywords corresponding to the measured semantic features, screening an intention condition combination meeting the correspondence between each semantic feature and the number of the keywords from all the intention condition combinations;

and determining a corresponding expected graph according to the screened intention condition combination.

In this embodiment, the expected graph is determined by the predicted intentions, wherein the expected graphs (the counter graph, the histogram, the pie graph, the two columns of histograms, the horizontal histogram and the aggregation histogram) respectively correspond to keywords (count, distribution, proportion, contrast, primary and secondary distribution and relevance) of one intention, and the intention of the predicted user query statement is determined by an intention condition combination, and the intention condition combination is composed of conditions, dimensions, calculation methods and the number of keywords correspondingly included in semantic features of the measurement. The corresponding scenes of each combination of intention conditions are as follows:

1. the intention condition combination for counting the keywords corresponding to the counting graph comprises the following steps:

a. the condition F is not equal to 0, the dimension D is 0, the calculation method M is 0, and the metric M is 0;

b. calculating the method M is 0 and the metric M is 0;

2. the intention condition combination of the distribution of the keywords corresponding to the histogram comprises the following steps:

a. d is 1, M is 0, and M is 0;

b. d is 1, M is 0, and M is 1;

c. d is 1, M is 1, and M is 1;

d. d is 1, M is 2, and M is 2;

3. the combination of intention conditions with keywords as proportion corresponding to the pie chart comprises:

a. the dimension D is 1 and the dimension D is,

b. d is 1, M is 0, and M is 1;

c. d is 0, M is 1, and M is 1;

d. d is 2, M is 0, and M is 1;

e. d is 2, M is 1, and M is 2;

4. the intention condition combination for comparing the keywords corresponding to the two columns of bar graphs comprises the following steps:

a. d is 1, M is 2, and M is 2;

b. d is 1, M is 1, and M is 1;

c. the condition F is 2, the calculation method M is 1, and the metric M is 1;

d. the condition F is 2, the calculation method M is 2, and the metric M is 2;

5. the intention condition combination with the keywords as primary and secondary distribution corresponding to the horizontal histogram comprises the following steps:

a. d is 2, M is 0, and M is 0;

b. d is 2, M is 1, and M is 1;

c. d is 2, M is 0, and M is 1;

6. the combination of intention conditions for aggregating keywords corresponding to the histogram as relevance includes:

a. d is 2, M is 0, and M is 0;

b. d is 2, M is 1, and M is 1;

in the above, scenes of corresponding intention condition combinations are set according to the number of the semantic features corresponding to the keywords, and each intention condition combination corresponds to the keyword to be displayed by the prediction graph, so that the prediction graph corresponding to the intention of the query statement of the prediction user is obtained.

Further, in one embodiment, the predicting step further comprises:

and when the number of the keywords contained in the counted intention semantic features is not zero, judging that the intention of the query sentence input by the user is clear, and retrieving in the database according to the query sentence to obtain a retrieval result and displaying the retrieval result to the user.

Further, the predicting the intention of the query statement according to the counted number of the keywords corresponding to the semantic features of the condition, the dimension, the calculation method and the measurement according to a preset matching rule further includes:

when the number of the keywords corresponding to the statistical conditions, dimensions, calculation methods and measured semantic features is predicted according to a preset matching rule to obtain two intention scenes, the word2vec is used for analyzing the semantic application scenes of the keywords of the query statement and determining the intention corresponding to the semantic application scenes of the query statement.

For example, the query statement is a keyword "distribution" of "distribution ratio of average ages of professions of students in Shanghai," and "the ratio" are semantic features of intention, at this time, the word2vec is used to analyze an application scenario of the query statement, that is, the average value of the analyzed ages reflects an age display rule more conforming to the application scenario and professions of the students in Shanghai by distribution than by adopting the ratio, so that the intention of the query statement is determined to be distribution, and a corresponding expected graph is a histogram.

In an alternative embodiment, the query statement is "average age of profession of students in shanghai", the number of keywords included in each semantic feature counted is defined as F ═ 1, dimension D ═ 2, calculation method, M ═ 1, metric, M ═ 1, intention: i is 0. The statistical result corresponds to two intentions of primary and secondary distribution and relevance in the preset matching rule, and the intention corresponding to the semantic application scene of the query statement can be screened out by analyzing the semantic application scene of the keyword of the query statement through the word2 vec.

A generation step: and correcting the query statement according to the predicted intention, performing data retrieval on a database to obtain target data, and generating an expected graph corresponding to the query statement and a data table contained in the expected graph according to the target data.

The data sheet is a data analysis record sheet and comprises results which are graphically displayed for data analysis and are presented to a user. And correcting the query statement according to the predicted intention, wherein the correction can be to complement the intention keywords in the query statement, retrieve target data from a database according to the corrected query statement, generate an expected graph corresponding to the query statement and a data table contained in the expected graph, and output the data table for a user to use.

Referring to FIG. 2, a block diagram of a preferred embodiment of the intent query program 10 of FIG. 1 is shown.

In one embodiment, the intent query program 10 includes: the device comprises a receiving module 101, a statistic module 102, a prediction module 103 and a generating module 104. The functions or operation steps implemented by the module 101-104 are similar to the following artificial intelligence-based user intention prediction method, which is not detailed here, for example, among others:

a receiving module 101, configured to receive a query statement input by a user through a terminal, analyze the query statement, and extract a plurality of keywords;

the statistic module 102 is configured to input the keywords into a pre-trained recognition model, extract semantic features corresponding to the keywords, and count the number of the keywords included in each semantic feature, where the semantic features include conditions, dimensions, a calculation method, metrics, and intentions;

the prediction module 103 is configured to, when the number of keywords included in the counted intention semantic features is zero, determine that the intention of the query sentence input by the user is ambiguous, predict the intention of the query sentence according to a preset matching rule based on the counted number of keywords included in semantic features corresponding to the counted conditions, dimensions, calculation methods, and measured semantic features, where each predicted intention corresponds to an expected graph;

and the generating module 104 is configured to correct the query statement according to the predicted intention, perform data retrieval on a database to obtain target data, and generate an expected graph corresponding to the query statement and a data table included in the expected graph according to the target data.

Referring to FIG. 3, a flow chart of a preferred embodiment of the method for predicting user intention based on artificial intelligence according to the present invention is shown. The invention discloses a user intention prediction method based on artificial intelligence, which is applied to the electronic device and comprises the following steps:

step S210, receiving a query sentence input by a user through a terminal, analyzing the query sentence and extracting a plurality of keywords.

For example, in one embodiment, a user inputs a query sentence of "Shanghai male career distribution" through a terminal (such as a computer, a mobile phone or an application APP), identifies and analyzes sentence components of the query sentence, analyzes keywords (such as keywords: Shanghai, male, career and distribution) of the query sentence, and extracts the keywords.

Step S220, inputting the keywords into a pre-trained recognition model, extracting semantic features corresponding to the keywords, and counting the number of the keywords contained in each semantic feature, wherein the semantic features comprise conditions, dimensions, a calculation method, measurement and intention.

In this implementation, the semantic features of conditions, dimensions, calculation methods, measures and intentions corresponding to the keywords are extracted through the recognition model, and the number of the included keywords of each semantic feature is counted.

The conditional semantic features are denoted by f (filter), and refer to keywords as data filtering or filtering, such as "shanghai", "male";

the dimension semantic features are denoted by d (dimension), which refers to the dimension in which the final graphic presentation specifically presents the keywords, such as "occupation";

the computational method semantic features are denoted m (method), referring to keywords for the computation of metrics, such as "average";

the metric semantic features are expressed by m (measure), and refer to a keyword as a statistical object, such as "age";

the intention semantic feature is denoted by i (intent), and refers to a graphical presentation result that the user desires to obtain, such as "distribution".

Further, the pre-trained recognition model comprises:

acquiring a keyword;

classifying preset semantic features according to the field attributes of the keywords, wherein the semantic features comprise conditions, dimensions, a calculation method, measurement and intentions;

and training an identification model based on the keywords contained in each semantic feature obtained by classification to obtain the semantic features corresponding to the keywords, and finishing the training of the identification model.

Specifically, the recognition model is a deep learning model, and can perform semantic understanding according to field attributes of the trained keywords and recognize semantic features corresponding to the keywords, wherein the semantic features include conditions, dimensions, a calculation method, measurement and intention. When a plurality of keywords are extracted from the query sentence input by the user, the semantic features corresponding to each keyword can be identified through the identification model.

For example, in one embodiment, the query sentence input by the user is "shanghai male different occupational average age distribution", the extracted keywords are "shanghai", "male", "occupational", "average", "age" and "distribution", and the conditional semantic features obtained by using the recognition model are "shanghai", "male"; the dimension semantic features are "profession"; the semantic features of the calculation method are 'average'; the metric semantic feature is "age"; the intent semantic feature is "distribution".

Step S230, when the number of the keywords contained in the counted intention semantic features is zero, judging that the intention of the query sentence input by the user is ambiguous, predicting the intention of the query sentence according to the counted condition, dimension, calculation method and the number of the keywords contained in the semantic features corresponding to the measured semantic features according to a preset matching rule, wherein each predicted intention corresponds to an expected graph.

When the intent of the query statement is ambiguous, it is difficult for the system to give a correct graphical presentation. In order to overcome this difficulty, the present embodiment predicts the intention of the query statement according to a preset matching rule by using the counted number of keywords included in correspondence to the semantic features of the conditions, dimensions, calculation methods, and metrics, so as to perform intention completion on the query statement with an ambiguous intention input by the user.

In this embodiment, a type of expected pattern is preset for each predicted intention. The keywords of the intention comprise counts, distribution, proportion, comparison, primary distribution and secondary distribution and correlation, the expected graphs comprise a count graph, a histogram, a pie graph, a two-column histogram, a horizontal histogram and a polymerization histogram, and each keyword of the intention corresponds to each expected graph respectively. For example,

a. if the keyword of the intention of the query sentence of 'how many people are in Shanghai male' is the count, the corresponding expected graph is displayed by a digital graph;

b. if the keywords of the intention of the query statement of 'Shanghai male occupation distribution' are distributed, the corresponding expected graph is displayed by a histogram;

c. if the keyword of the intention that the query statement is 'Shanghai male unmarried proportion' is a proportion, the corresponding expected graph is displayed in a pie chart;

d. if the keyword of the intention of the query statement of 'income comparison between men and women' is comparison, the corresponding expected graph is displayed in two columns of bar graphs;

e. the keywords of the intention of the query sentence which is 'what the first ten jobs with higher average income are' are distributed primarily and secondarily, and the corresponding expected graph is displayed by a horizontal histogram;

f. the query statement is "how relevant are careers and academic records? "the intended keyword is a relevance, the corresponding expected graph is shown as an aggregate histogram.

Further, the preset matching rule further includes:

classifying intention condition combinations corresponding to each expected graph according to the expected graphs, wherein each intention condition combination is composed of one or more of conditions, dimensions, calculation methods and measured semantic features;

according to the pre-counted conditions, dimensions, a calculation method and the number of keywords corresponding to the measured semantic features, screening an intention condition combination meeting the correspondence between each semantic feature and the number of the keywords from all the intention condition combinations;

and determining a corresponding expected graph according to the screened intention condition combination.

In this embodiment, the expected graph is determined by the predicted intentions, wherein the expected graphs (the counter graph, the histogram, the pie graph, the two columns of histograms, the horizontal histogram and the aggregation histogram) respectively correspond to keywords (count, distribution, proportion, contrast, primary and secondary distribution and relevance) of one intention, and the intention of the predicted user query statement is determined by an intention condition combination, and the intention condition combination is composed of conditions, dimensions, calculation methods and the number of keywords correspondingly included in semantic features of the measurement. The corresponding scenes of each combination of intention conditions are as follows:

1. the intention condition combination for counting the keywords corresponding to the counting graph comprises the following steps:

a. the condition F is not equal to 0, the dimension D is 0, the calculation method M is 0, and the metric M is 0;

b. calculating the method M is 0 and the metric M is 0;

2. the intention condition combination of the distribution of the keywords corresponding to the histogram comprises the following steps:

a. d is 1, M is 0, and M is 0;

b. d is 1, M is 0, and M is 1;

c. d is 1, M is 1, and M is 1;

d. d is 1, M is 2, and M is 2;

3. the combination of intention conditions with keywords as proportion corresponding to the pie chart comprises:

a. the dimension D is 1 and the dimension D is,

b. d is 1, M is 0, and M is 1;

c. d is 0, M is 1, and M is 1;

d. d is 2, M is 0, and M is 1;

e. d is 2, M is 1, and M is 2;

4. the intention condition combination for comparing the keywords corresponding to the two columns of bar graphs comprises the following steps:

a. d is 1, M is 2, and M is 2;

b. d is 1, M is 1, and M is 1;

c. the condition F is 2, the calculation method M is 1, and the metric M is 1;

d. the condition F is 2, the calculation method M is 2, and the metric M is 2;

5. the intention condition combination with the keywords as primary and secondary distribution corresponding to the horizontal histogram comprises the following steps:

a. d is 2, M is 0, and M is 0;

b. d is 2, M is 1, and M is 1;

c. d is 2, M is 0, and M is 1;

6. the combination of intention conditions for aggregating keywords corresponding to the histogram as relevance includes:

a. d is 2, M is 0, and M is 0;

b. d is 2, M is 1, and M is 1;

in the above, scenes of corresponding intention condition combinations are set according to the number of the semantic features corresponding to the keywords, and each intention condition combination corresponds to the keyword to be displayed by the prediction graph, so that the prediction graph corresponding to the intention of the query statement of the prediction user is obtained.

Further, in one embodiment, the step S230 further includes:

and when the number of the keywords contained in the counted intention semantic features is not zero, judging that the intention of the query sentence input by the user is clear, and retrieving in the database according to the query sentence to obtain a retrieval result and displaying the retrieval result to the user.

Further, the predicting the intention of the query statement according to the counted number of the keywords corresponding to the semantic features of the condition, the dimension, the calculation method and the measurement according to a preset matching rule further includes:

when the number of the keywords corresponding to the statistical conditions, dimensions, calculation methods and measured semantic features is predicted according to a preset matching rule to obtain two intention scenes, the word2vec is used for analyzing the semantic application scenes of the keywords of the query statement and determining the intention corresponding to the semantic application scenes of the query statement.

For example, the query statement is a keyword "distribution" of "distribution ratio of average ages of professions of students in Shanghai," and "the ratio" are semantic features of intention, at this time, the word2vec is used to analyze an application scenario of the query statement, that is, the average value of the analyzed ages reflects an age display rule more conforming to the application scenario and professions of the students in Shanghai by distribution than by adopting the ratio, so that the intention of the query statement is determined to be distribution, and a corresponding expected graph is a histogram.

In an alternative embodiment, the query statement is "average age of profession of students in shanghai", the number of keywords included in each semantic feature counted is defined as F ═ 1, dimension D ═ 2, calculation method, M ═ 1, metric, M ═ 1, intention: i is 0. The statistical result corresponds to two intentions of primary and secondary distribution and relevance in the preset matching rule, and the intention corresponding to the semantic application scene of the query statement can be screened out by analyzing the semantic application scene of the keyword of the query statement through the word2 vec.

And S240, correcting the query statement according to the predicted intention, performing data retrieval on a database to obtain target data, and generating an expected graph corresponding to the query statement and a data table contained in the expected graph according to the target data.

The data sheet is a data analysis record sheet and comprises results which are graphically displayed for data analysis and are presented to a user. And correcting the query statement according to the predicted intention, wherein the correction can be to complement the intention keywords in the query statement, retrieve target data from a database according to the corrected query statement, generate an expected graph corresponding to the query statement and a data table contained in the expected graph, and output the data table for a user to use.

Furthermore, the present invention also provides a computer-readable storage medium, which includes an intention query program, and when the intention query program is executed by a processor, the intention query program can implement the following operations:

a receiving step: receiving a query sentence input by a user through a terminal, analyzing the query sentence and extracting a plurality of keywords;

a statistical step: inputting the keywords into a pre-trained recognition model, extracting semantic features corresponding to the keywords, and counting the number of the keywords contained in each semantic feature, wherein the semantic features comprise conditions, dimensions, a calculation method, measurement and intention;

a prediction step: when the number of the keywords contained in the counted intention semantic features is zero, judging that the intention of the query statement input by a user is ambiguous, predicting the intention of the query statement according to the counted conditions, dimensions, a calculation method and the number of the keywords contained in the semantic features measured according to a preset matching rule, wherein each predicted intention corresponds to an expected graph;

a generation step: and correcting the query statement according to the predicted intention, performing data retrieval on a database to obtain target data, and generating an expected graph corresponding to the query statement and a data table contained in the expected graph according to the target data.

The embodiment of the computer-readable storage medium of the present invention is substantially the same as the embodiments of the artificial intelligence based user intention prediction method and the electronic device, and will not be described herein again.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (10)

1. A user intention prediction method based on artificial intelligence is applied to an electronic device and is characterized by comprising the following steps:

a receiving step: receiving a query sentence input by a user through a terminal, analyzing the query sentence and extracting a plurality of keywords;

a statistical step: inputting the keywords into a pre-trained recognition model, extracting semantic features corresponding to the keywords, and counting the number of the keywords contained in each semantic feature, wherein the semantic features comprise conditions, dimensions, a calculation method, measurement and intention;

a prediction step: when the number of the keywords contained in the counted intention semantic features is zero, judging that the intention of the query statement input by a user is ambiguous, predicting the intention of the query statement according to the counted conditions, dimensions, a calculation method and the number of the keywords contained in the semantic features measured according to a preset matching rule, wherein each predicted intention corresponds to an expected graph;

a generation step: and correcting the query statement according to the predicted intention, performing data retrieval on a database to obtain target data, and generating an expected graph corresponding to the query statement and a data table contained in the expected graph according to the target data.

2. The artificial intelligence-based user intent prediction method of claim 1, wherein the pre-trained recognition model comprises:

acquiring a keyword;

classifying preset semantic features according to the field attributes of the keywords, wherein the semantic features comprise conditions, dimensions, a calculation method, measurement and intentions;

and training an identification model based on the keywords contained in each semantic feature obtained by classification to obtain the semantic features corresponding to the keywords, and finishing the training of the identification model.

3. The artificial intelligence based user intent prediction method of claim 1, wherein the preset matching rules comprise:

classifying intention condition combinations corresponding to each expected graph according to the expected graphs, wherein each intention condition combination is composed of one or more of conditions, dimensions, calculation methods and measured semantic features;

according to the pre-counted conditions, dimensions, a calculation method and the number of keywords corresponding to the measured semantic features, screening an intention condition combination meeting the correspondence between each semantic feature and the number of the keywords from all the intention condition combinations;

and determining a corresponding expected graph according to the screened intention condition combination.

4. The artificial intelligence based user intent prediction method of claim 1, wherein the prediction step further comprises:

and when the number of the keywords contained in the counted intention semantic features is not zero, judging that the intention of the query sentence input by the user is clear, and retrieving in the database according to the query sentence to obtain a retrieval result and displaying the retrieval result to the user.

5. The artificial intelligence based user intention prediction method according to any one of claims 1 to 4, wherein the method for predicting the intention of the query sentence according to the number of keywords included in correspondence with the statistical conditions, dimensions, calculation methods and measured semantic features according to a preset matching rule further comprises:

when the number of the keywords corresponding to the counted conditions, dimensions, calculation methods and measured semantic features is predicted according to a preset matching rule to obtain two intention scenes, the word2vec is used for analyzing the semantic application scenes of the keywords of the query statement and determining the intention corresponding to the semantic application scenes of the query statement.

6. An electronic device comprising a memory and a processor, the memory having stored therein an intent query program operable on the processor, the intent query program when executed by the processor implementing the steps of:

a receiving step: receiving a query sentence input by a user through a terminal, analyzing the query sentence and extracting a plurality of keywords;

a statistical step: inputting the keywords into a pre-trained recognition model, extracting semantic features corresponding to the keywords, and counting the number of the keywords contained in each semantic feature, wherein the semantic features comprise conditions, dimensions, a calculation method, measurement and intention;

a prediction step: when the number of the keywords contained in the counted intention semantic features is zero, judging that the intention of the query statement input by a user is ambiguous, predicting the intention of the query statement according to the counted conditions, dimensions, a calculation method and the number of the keywords contained in the semantic features measured according to a preset matching rule, wherein each predicted intention corresponds to an expected graph;

a generation step: and correcting the query statement according to the predicted intention, performing data retrieval on a database to obtain target data, and generating an expected graph corresponding to the query statement and a data table contained in the expected graph according to the target data.

7. The electronic device of claim 6, wherein the pre-trained recognition model comprises:

acquiring a keyword;

classifying preset semantic features according to the field attributes of the keywords, wherein the semantic features comprise conditions, dimensions, a calculation method, measurement and intentions;

and training an identification model based on the keywords contained in each semantic feature obtained by classification to obtain the semantic features corresponding to the keywords, and finishing the training of the identification model.

8. The electronic device of claim 6, wherein the preset matching rule further comprises:

classifying intention condition combinations corresponding to each expected graph according to the expected graphs, wherein each intention condition combination is composed of one or more of conditions, dimensions, calculation methods and measured semantic features;

according to the pre-counted conditions, dimensions, a calculation method and the number of keywords corresponding to the measured semantic features, screening an intention condition combination meeting the correspondence between each semantic feature and the number of the keywords from all the intention condition combinations;

and determining a corresponding expected graph according to the screened intention condition combination.

9. The electronic device of claim 6, wherein the predicting step further comprises:

and when the number of the keywords contained in the counted intention semantic features is not zero, judging that the intention of the query sentence input by the user is clear, and retrieving in the database according to the query sentence to obtain a retrieval result and displaying the retrieval result to the user.

10. A computer-readable storage medium, comprising an intent query program that, when executed by a processor, performs the steps of the artificial intelligence based user intent prediction method of any one of claims 1 to 5.

Images