CN115687618A - User intention analysis method and system based on artificial intelligence - Google Patents
User intention analysis method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN115687618A CN115687618A CN202211264226.3A CN202211264226A CN115687618A CN 115687618 A CN115687618 A CN 115687618A CN 202211264226 A CN202211264226 A CN 202211264226A CN 115687618 A CN115687618 A CN 115687618A
- Authority
- CN
- China
- Prior art keywords
- user
- examples
- commonality
- category
- description knowledge
- 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.)
- Withdrawn
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
According to the user intention analysis method and system based on artificial intelligence, first user intention description knowledge of a user consultation information example set needing to be analyzed is obtained; determining a common factor among examples in a user consultation information example set according to the first user intention description knowledge of the examples to obtain a first common factor queue; mining the first user intention description knowledge of the example based on the first common factor queue to obtain second user intention description knowledge of the example, and determining common factors among examples in the user consultation information example set according to the second user intention description knowledge of the example to obtain a second common factor queue; and analyzing the examples of the common factors exceeding the common factor specified value based on the second common factor queue to obtain the user interest heat theme. The user intention can be analyzed more accurately, and the user can be pushed with accurate information according to the intention of the user, so that the experience of the user is improved.
Description
Technical Field
The application relates to the technical field of data analysis, in particular to a user intention analysis method and system based on artificial intelligence.
Background
Data analysis refers to the process of analyzing a large amount of collected data by using an appropriate statistical analysis method, extracting useful information and forming a conclusion to study and summarize the data in detail. This process is also a support process for the quality management architecture. In practice, data analysis may help people make decisions in order to take appropriate action.
Currently, when a data analysis technology is applied to a specific operation process, the intention of a user is analyzed, and the problem of inaccurate user intention analysis caused by various interferences may exist. Therefore, a technical solution is needed to improve the above technical problems.
Disclosure of Invention
In order to solve the technical problems in the related art, the application provides a user intention analysis method and system based on artificial intelligence.
In a first aspect, a method for analyzing user intention based on artificial intelligence is provided, which is applied to a system for analyzing user intention, and the method at least includes: obtaining first user intention description knowledge of examples in a user consultation information example set which needs to be analyzed; determining a common factor among examples in a user consultation information example set according to the first user intention description knowledge of the examples to obtain a first common factor queue; mining the example first user intention description knowledge to obtain example second user intention description knowledge based on the first commonality factor queue, wherein the example second user intention description knowledge is used for replacing the first user intention description knowledge and is determined as an example intention description knowledge description; determining a commonality factor among examples in the user consultation information example set according to the second user intention description knowledge of the examples to obtain a second commonality factor queue; and analyzing the examples of the common factors exceeding the specified value of the common factors based on the second common factor queue to obtain the user interest heat theme.
In an independently implemented embodiment, before performing the step of determining a commonality factor between examples in a user's consulting information example set of examples according to the first user intent description knowledge of examples, resulting in a first commonality factor queue, comprises: and carrying out dimensionless simplification operation on the first user intention description knowledge of the example to obtain the first user intention description knowledge of the example after the dimensionless simplification operation.
In an embodiment of an independent implementation, the performing a dimensionless reduction operation on the example user intention description knowledge to obtain the example user intention description knowledge after the dimensionless reduction operation includes: determining an intermediate value and a sample comparison value of the user intent description knowledge exemplified in the set of user advisory information examples; for a random example in the user consultation information example set, determining the comparison result of the user intention description knowledge of the example and the intermediate value, and determining the weighting processing result of the comparison result and the sample comparison value as the user intention description knowledge of the example after the dimensionless simplification operation.
In an independently implemented embodiment, before performing the step of mining the example first user intent description knowledge based on the first common factor queue to obtain the example second user intent description knowledge, the method includes: and performing data sampling operation on the first commonality factor queue to obtain the data-sampled first commonality factor queue.
In an embodiment, the performing a data sampling operation on the first commonality factor queue to obtain a data-sampled first commonality factor queue includes: for a random sample-related commonality factor in a user consultation information sample set, keeping a designated number of commonality factors with a higher priority level, and recording the remaining commonality factors as x to obtain a first commonality factor queue after data sampling; wherein x is zero.
In an independently implemented embodiment, the mining the example first user intention describing knowledge based on the first commonality factor queue to obtain the example second user intention describing knowledge includes: combining the user consultation information example set and the first common factor queue to construct a nonlinear label of the user consultation information example set, wherein the user consultation elements in the nonlinear label represent examples, and a neighboring part between two user consultation elements represents a non-x common factor between the two user consultation elements; for a random one of the user consulting elements carrying a contiguous portion in the non-linear label, determining a first calculation result of the first commonality factor queue and a second calculation result of the first user intention description knowledge of the example as a second user intention description knowledge of the example.
In an independently implemented embodiment, the analyzing, based on the second commonality factor queue, the example that the commonality factor exceeds the designated value of the commonality factor to obtain the topic of user interest heat, includes: in the nonlinear tag, two user consultation elements which carry adjacent parts and have the common factor exceeding the specified value of the common factor in a second common factor queue are searched, and the two searched user consultation elements are fused into the same category to obtain the user interest heat topic.
In an independently implemented embodiment, the step of analyzing the examples of which the commonality factors exceed the designated value of the commonality factors based on the second commonality factor queue to obtain the topic of user interest heat after the step of executing the example set of user consulting information needing to be analyzed as the user preference set includes: for a random one of the user interest heat topics, determining an intermediate value of second user intention description knowledge exemplified in the category as the user intention description knowledge of the category; determining the number of examples of each category in the user interest heat topic; determining the categories of which the number of examples in the user interest heat topic meets the specified number value as important categories, and determining the categories of which the number of examples does not meet the specified number value as secondary categories; for a random secondary category, merging the examples of the secondary category into an important category with the highest commonality factor with the secondary category, and optimizing the user intention description knowledge of the important category after integrating the secondary category; judging whether the number of important categories is different from the number of examples in the user consultation information example set and whether the number of important categories is larger than y; when the number of the important categories is different from the number of examples in the user consultation information example set and the number of the important categories is larger than y, determining an important user interest heat topic as the optimized user consultation information example set, continuously executing the first user intention description knowledge according to the examples, determining common factors among the examples in the user consultation information example set, and obtaining a first common factor queue; wherein y is 1.
In an embodiment of an independent implementation, after the steps of determining the important user interest popularity topic as a user consulting information example set, executing the second commonality factor-based queue, analyzing examples in which the commonality factors exceed the commonality factor specified values, and obtaining the user interest popularity topic include: judging whether the number of the categories is different from the number of examples in the user consultation information example set and whether the number of the categories in the user interest heat topic is larger than y; and when the number of the categories is different from the number of examples in the user consultation information example set and the number of the categories is larger than y, determining the user interest heat topic as the optimized user consultation information example set, and continuously executing the first user intention description knowledge according to the examples, determining the common factors among the examples in the user consultation information example set, and obtaining a first common factor queue.
In a separately implemented embodiment, comprising: for each category in the user interest heat topic, generating a category indication of the category; searching user preference information in a category corresponding to the category indication in combination with the category indication; the method comprises the steps of obtaining user intention description knowledge of user preference needing to be classified, associating the user intention description knowledge of the user preference needing to be classified with user intention description knowledge of each category in a user interest heat theme, and determining a category indication of the category with the highest association degree as the category indication of the user preference needing to be classified.
In a second aspect, an artificial intelligence based user intent analysis system is provided, comprising a processor and a memory in communication with each other, the processor being configured to read a computer program from the memory and execute the computer program to implement the method described above.
According to the method and the system for analyzing the user intention based on the artificial intelligence, first user intention description knowledge of a user consultation information example set needing to be analyzed is obtained; determining a common factor among examples in a user consultation information example set according to the first user intention description knowledge of the examples to obtain a first common factor queue; mining the first user intention description knowledge of the example based on the first common factor queue to obtain second user intention description knowledge of the example, and determining common factors among examples in the user consultation information example set according to the second user intention description knowledge of the example to obtain a second common factor queue; and analyzing the examples of the common factors exceeding the specified value of the common factors based on the second common factor queue to obtain the user interest heat theme. Therefore, the user intention can be analyzed more accurately, the user can be pushed with accurate information according to the intention of the user, and the experience of the user is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart of a user intention analysis method based on artificial intelligence according to an embodiment of the present disclosure.
Fig. 2 is a block diagram of an artificial intelligence-based user intention analysis apparatus according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions, the technical solutions of the present application are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.
Referring to fig. 1, a method for analyzing user intention based on artificial intelligence is shown, which may include the technical solutions described in the following steps S201 to S205.
In step S201, first user intention description knowledge exemplified in a user consultation information example set that needs to be analyzed is obtained. The user intention description knowledge extraction may be performed on the examples, such as by using an artificial intelligence thread for user intention description knowledge extraction.
In step S202, according to the first user intention description knowledge of the examples, a commonality factor between examples in the user consultation information example set is determined, resulting in a first commonality factor queue. Step S202 may determine a commonality factor between examples, such as based on a commonality calculation function. In addition, one example has a commonality factor with itself of 1.
In step S203, mining the example first user intent description knowledge based on the first commonality factor queue to obtain the example second user intent description knowledge. Wherein the example second user intent description knowledge is used in place of the first user intent description knowledge and determined as an example intent description knowledge depiction. The mining process may debug the intent description knowledge depiction of the example.
In step S204, according to the second user intention description knowledge of the examples, the user is determined to consult the commonality factors between the examples in the information example set, resulting in a second commonality factor queue.
In step S205, based on the second commonality factor queue, the example in which the commonality factor exceeds the designated value of the commonality factor is analyzed to obtain the user interest topic.
In conclusion, first user intention description knowledge of a user consultation information sample set needing to be analyzed is obtained; determining a common factor among examples in a user consultation information example set according to the first user intention description knowledge of the examples to obtain a first common factor queue; mining the first user intention description knowledge of the example based on the first common factor queue to obtain second user intention description knowledge of the example, and determining common factors among examples in the user consultation information example set according to the second user intention description knowledge of the example to obtain a second common factor queue; and analyzing the examples of the common factors exceeding the specified value of the common factors based on the second common factor queue to obtain the user interest heat theme. Therefore, the user intention can be analyzed more accurately, the user can be pushed with accurate information according to the intention of the user, and the experience of the user is improved.
An artificial intelligence based user intent analysis method according to some embodiments of the present application. The method may comprise the following steps.
In step S301, first user intention description knowledge exemplified in a set of user consultation information examples that need to be analyzed is obtained. Here, the exemplary set of user consultation information is, for example, a set of user preferences. Step S301 may perform user intention description knowledge extraction on the example, for example, by using an artificial intelligence thread for user intention description knowledge extraction, or the like. Here, the first user intention describing knowledge obtained in step S301 may be characterized as one or more user intention describing knowledge vectors, for example.
In step S302, a dimensionless reduction operation is performed on the first user intention describing knowledge of the example, so as to obtain the first user intention describing knowledge of the example after the dimensionless reduction operation. Here, through dimensionless simplification operations, the intended description knowledge delineation of commonality factors in different examples can be made more similar in order to improve the accuracy of the analysis.
In a possible implementation example, the step S302 is further described, and specifically includes the following steps.
In step S401, an intermediate value of the user intention description knowledge and a sample comparison value of the examples in the user consultation information example set are determined.
In step S402, for a random one of the example set of user consultation information, the result of comparison of the user intention describing knowledge of the example with the intermediate value is determined, and the result of weighting processing of the difference with the sample comparison value is determined as the user intention describing knowledge of the example after the dimensionless reduction operation.
It will be appreciated that the user intent description knowledge characterization of the examples is tuned based on the depolarization comparison results and the sample comparison values so that the intent description knowledge delineation of the commonality factors is more similar in different examples, thereby improving the accuracy of the analysis.
In step S303, according to the first user intention description knowledge of the examples, a commonality factor between examples in the user consultation information example set is determined, resulting in a first commonality factor queue.
In step S304, a data sampling operation is performed on the first commonality factor queue to obtain a first commonality factor queue of data sampling.
In one possible implementation, for a commonality factor associated with a random one of the example sets of user advisory information, a specified number of commonality factors with an earlier priority are retained and the remaining commonality factors are recorded as x to obtain a data sampled first queue of commonality factors.
It will be appreciated that examples with a low commonality factor can be considered to belong to different categories. Therefore, by the data sampling operation, the speed of analysis can be increased without disturbing the reliability of the analysis.
In step S305, mining processing is performed on the example first user intention describing knowledge based on the first common factor queue to obtain example second user intention describing knowledge. Wherein the example second user intent description knowledge is used in place of the first user intent description knowledge and determined as an example intent description knowledge depiction. The mining process may debug the intent description knowledge depiction of the example.
In a possible implementation example, step S305 is further described, and specifically may include the following steps.
In step S501, a non-linear label of the user consulting information example set is constructed according to the user consulting information example set and the first common factor queue. Wherein the user advisory elements in the non-linear label characterize an example, and the neighborhood between two user advisory elements characterizes a non-x commonality factor between the two user advisory elements.
For example, the user consults the elements m1 to m4. Wherein m1 to m3 carry a contiguous moiety. Whereas m4 has no adjoining part. Each example represented by the user advisory factors m1 to m3 carries a non-x commonality factor with the remaining examples. And the example represented by the user counseling element m4 has a commonality factor of zero with the remaining user counseling elements.
In step S502, for a random one of the user consulting elements carrying the adjacent part in the non-linear tag, a second calculation result of the first common factor queue and the first user intention describing knowledge of the example is determined as the second user intention describing knowledge of the example.
It can be understood that, due to the data sampling operation of step S304, the processing (i.e., mining processing) of the user consulting elements not carrying the adjacent parts can be avoided, so that the accuracy of the data sampling operation can be improved.
In summary, by mining processing, the intention description knowledge depiction of the examples can be debugged, so that the enhancement degree of the commonality factor between the examples with higher commonality factors is higher, and the fusion of the examples is accelerated and the examples are analyzed accurately.
In step S306, according to the second user intention description knowledge of the examples, the user is determined to consult the commonality factors between the examples in the information example set, resulting in a second commonality factor queue.
For example, based on example second user intent description knowledge step S306 may generate a second commonality factor queue
In step S307, based on the second commonality factor queue, an example in which the commonality factor exceeds the designated value of the commonality factor is analyzed to obtain the user interest topic.
In one possible implementation example, step S307 may find two user query elements carrying adjacent parts and having a commonality factor exceeding a designated value of the commonality factor in the second commonality factor queue in the nonlinear tag, and merge the two found user query elements into the same category to obtain the topic of user interest heat.
In step S308, for a random one of the categories in the user interest popularity topics, an intermediate value of the second user intention description knowledge exemplified in the category is determined as the user intention description knowledge of the category.
In step S309, the number of examples of each category in the topic of user interest heat is counted.
In step S310, the categories of which the number of examples in the user interest heat topic satisfies the number designation value are determined as important categories, and the categories of which the number of examples does not satisfy the number designation value are determined as minor categories.
In step S311, for a random secondary category, merging the examples of the secondary category into the important category with the highest commonality factor with the secondary category, and optimizing the user intention description knowledge of the important category after integrating the secondary category. Here, optimizing the user intention describing knowledge of the important category is to recalculate an intermediate value of the second user intention describing knowledge exemplified in the important category.
In step S312, it is determined whether the number of important categories is different from the number of examples in the user consultation information example set and whether the number of important categories is greater than y. Here, step S312 may determine whether the analysis process needs to be performed again. If the number of important categories is the same as the number of examples in the user advisory information example set and the number of important categories is not greater than y, the analysis does not need to be continued and the execution flow may be ended.
When it is determined in step S312 that the number of important categories is different from the number of examples in the user advisory information example set and the number of important categories is greater than y, the method may perform step S313, determine the important user interest heat topic as the optimized user advisory information example set, and continue to perform steps S314-S320. Here, the execution process of steps S314-S320 is similar to that of steps S302-S308, and is not described here again.
In step S321, it is determined whether the number of categories is different from the number of examples in the user consultation information example set and the number of categories in the user interest degree topic is greater than y.
When it is determined in step S321 that the number of categories is different from the number of examples in the user advisory information example set and the number of categories is greater than y, step S322 of determining the user heat of interest topic as the optimized user advisory information example set may be performed.
In step S324, according to the category indication, the user preference information in the category corresponding to the category indication is searched. When a certain category of user preferences is needed, the embodiment of the present application may search for the user preferences corresponding to the category indication through step S324.
In step S325, user intention description knowledge of the user preference that needs to be classified is obtained, the user intention description knowledge of the user preference that needs to be classified is associated with the user intention description knowledge of each category in the user interest popularity topic, and the category indication of the category with the highest association is determined as the category indication of the user preference that needs to be classified. Here, the user intention description knowledge of the user preference to be classified is associated with the user intention description knowledge of one category, for example, by determining a user intention description knowledge commonality factor.
On the basis, please refer to fig. 2 in combination, there is provided an artificial intelligence based user intention analysis apparatus 200, applied to an artificial intelligence based user intention analysis cloud platform, the apparatus comprising:
a knowledge acquisition module 210 for acquiring a first user intention description knowledge exemplified in a set of user consulting information examples that need to be analyzed;
a queue obtaining module 220, configured to determine a commonality factor between examples in the user consulting information example set according to the first user intention description knowledge of the examples, so as to obtain a first commonality factor queue;
a knowledge mining module 230, configured to mine the example first user intent description knowledge based on the first commonality factor queue to obtain example second user intent description knowledge, wherein the example second user intent description knowledge is used to replace the first user intent description knowledge and is determined as the example intent description knowledge depiction;
a factor determining module 240, configured to determine a commonality factor between examples in the user consultation information example set according to the second user intention description knowledge of the examples, so as to obtain a second commonality factor queue;
and the heat analysis module 250 is configured to analyze an example that the commonality factor exceeds the designated value of the commonality factor based on the second commonality factor queue to obtain a user interest heat topic.
On the basis of the above, an artificial intelligence based user intention analysis system 300 is shown, which comprises a processor 310 and a memory 320 which are communicated with each other, wherein the processor 310 is used for reading a computer program from the memory 320 and executing the computer program to realize the method.
On the basis of the above, there is also provided a computer-readable storage medium on which a computer program is stored, which when executed implements the above-described method.
In summary, based on the above scheme, the first user intention description knowledge of the example in the user consultation information sample set that needs to be analyzed is obtained; determining a common factor among examples in a user consultation information example set according to the first user intention description knowledge of the examples to obtain a first common factor queue; mining the first user intention description knowledge of the example based on the first common factor queue to obtain second user intention description knowledge of the example, and determining common factors among examples in the user consultation information example set according to the second user intention description knowledge of the example to obtain a second common factor queue; and analyzing the examples of the common factors exceeding the specified value of the common factors based on the second common factor queue to obtain the user interest heat theme. Therefore, the user intention can be analyzed more accurately, and the user can be pushed with accurate information according to the user intention, so that the experience of the user is improved.
It should be appreciated that the system and its modules shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, for example such code provided on a carrier medium such as a diskette, CD-or DVD-ROM, programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).
It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered as illustrative only and not limiting of the application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such alterations, modifications, and improvements are intended to be suggested herein and are intended to be within the spirit and scope of the exemplary embodiments of this application.
Also, this application uses specific language to describe embodiments of the application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means a feature, structure, or characteristic described in connection with at least one embodiment of the application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.
Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.
The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.
Computer program code required for operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C + +, C #, VB.NET, python, and the like, a conventional programming language such as C, visual Basic, fortran 2003, perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).
Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While certain presently contemplated useful embodiments of the invention have been discussed in the foregoing disclosure by way of various examples, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments of the disclosure. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in the foregoing description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the numbers allow for variation in flexibility. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.
Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, and the like, cited in this application is hereby incorporated by reference in its entirety. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application may be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those explicitly described and illustrated herein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.
Claims (10)
1. A user intention analysis method based on artificial intelligence is characterized by being applied to a user intention analysis system, and the method at least comprises the following steps:
obtaining first user intention description knowledge of examples in a user consultation information example set which needs to be analyzed;
determining a common factor among examples in a user consultation information example set according to the first user intention description knowledge of the examples to obtain a first common factor queue;
mining the example first user intention description knowledge to obtain example second user intention description knowledge based on the first commonality factor queue, wherein the example second user intention description knowledge is used for replacing the first user intention description knowledge and is determined as an example intention description knowledge description;
determining a commonality factor between examples in the user consultation information example set according to the second user intention description knowledge of the examples to obtain a second commonality factor queue;
and analyzing the examples of the common factors exceeding the specified value of the common factors based on the second common factor queue to obtain the user interest heat theme.
2. The method of claim 1, wherein prior to performing the step of determining a commonality factor between examples in a user's consulting information example set of knowledge of the first user's intent description according to examples to arrive at a first commonality factor queue, comprising: and carrying out dimensionless simplification operation on the first user intention description knowledge of the example to obtain the first user intention description knowledge of the example after the dimensionless simplification operation.
3. The method of claim 2, wherein the performing a dimensionless reduction operation on the example user intention description knowledge to obtain the example user intention description knowledge after the dimensionless reduction operation comprises:
determining an intermediate value and a sample comparison value of user intent description knowledge for an example in a user advisory information example set;
for a random example in the user consultation information example set, determining the comparison result of the user intention description knowledge of the example and the intermediate value, and determining the weighting processing result of the comparison result and the sample comparison value as the user intention description knowledge of the example after the dimensionless simplification operation.
4. The method of claim 1, prior to performing the step of mining the example first user intent description knowledge based on the first commonality factor queue to obtain the example second user intent description knowledge, comprising: and performing data sampling operation on the first commonality factor queue to obtain the data-sampled first commonality factor queue.
5. The method of claim 4, wherein the performing a data sampling operation on the first commonality factor queue to obtain a data-sampled first commonality factor queue comprises: for a random sample-related commonality factor in a user consultation information sample set, keeping a specified number of commonality factors with the prior priority level, and recording the residual commonality factors as x to obtain a first commonality factor queue after data sampling; wherein x is zero.
6. The method of claim 1, wherein mining the example first user intent description knowledge based on the first common factor queue to obtain the example second user intent description knowledge comprises:
combining the user consultation information example set and the first common factor queue to construct a nonlinear label of the user consultation information example set, wherein the user consultation elements in the nonlinear label represent examples, and a neighboring part between two user consultation elements represents a non-x common factor between the two user consultation elements;
for a random user consultation element carrying a contiguous part in the nonlinear label, determining a first calculation result of the first commonality factor queue and a second calculation result of the first user intention description knowledge of the example as a second user intention description knowledge of the example.
7. The method according to claim 6, wherein the analyzing the examples of the commonality factor exceeding the designated value of the commonality factor based on the second queue of commonality factors to obtain the topic of user heat of interest comprises:
in the nonlinear tag, two user consultation elements which carry adjacent parts and have the commonality factors exceeding the designated value of the commonality factors in the second commonality factor queue are searched, and the two searched user consultation elements are fused into the same category to obtain the user interest heat theme.
8. The method as claimed in claim 1, wherein the set of examples of user consulting information to be analyzed is a set of user preferences, and after the step of analyzing examples of which the commonality factors exceed the designated value of the commonality factors based on the second queue of commonality factors to obtain the topic of user interest heat is performed, the method comprises:
for a random one of the user interest heat topics, determining an intermediate value of second user intention description knowledge exemplified in the category as the user intention description knowledge of the category;
determining the number of examples of each category in the user interest heat topic;
determining the category of which the number of examples in the user interest heat topic meets a specified number value as an important category, and determining the category of which the number of examples does not meet the specified number value as a secondary category;
for a random secondary category, merging the examples of the secondary category into an important category with the highest similarity factor with the secondary category, and optimizing the user intention description knowledge of the important category after integrating the secondary category;
judging whether the number of important categories is different from the number of examples in the user consultation information example set and whether the number of important categories is larger than y;
when the number of the important categories is different from the number of examples in the user consultation information example set and the number of the important categories is larger than y, determining an important user interest heat topic as the optimized user consultation information example set, continuously executing the first user intention description knowledge according to the examples, determining common factors among the examples in the user consultation information example set, and obtaining a first common factor queue; wherein y is 1;
after the steps of determining the important user interest heat topic as a user consultation information example set, executing the second common factor queue, analyzing examples of which the common factors exceed the common factor specified value, and obtaining the user interest heat topic, the method comprises the following steps:
judging whether the number of the categories is different from the number of examples in the user consultation information example set and whether the number of the categories in the user interest heat topic is larger than y;
and when the number of the categories is different from the number of examples in the user consultation information example set and the number of the categories is larger than y, determining the user interest heat topic as the optimized user consultation information example set, and continuously executing the first user intention description knowledge according to the examples, determining the common factors among the examples in the user consultation information example set, and obtaining a first common factor queue.
9. The method of claim 1, comprising:
for each category in the user interest heat topic, generating a category indication of the category;
searching user preference information in a category corresponding to the category indication in combination with the category indication;
the method comprises the steps of obtaining user intention description knowledge of user preference needing to be classified, associating the user intention description knowledge of the user preference needing to be classified with user intention description knowledge of each category in a user interest heat theme, and determining a category indication of the category with the highest association degree as the category indication of the user preference needing to be classified.
10. An artificial intelligence based user intent analysis system comprising a processor and a memory in communication with each other, the processor for reading a computer program from the memory and executing to implement the method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211264226.3A CN115687618A (en) | 2022-10-17 | 2022-10-17 | User intention analysis method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211264226.3A CN115687618A (en) | 2022-10-17 | 2022-10-17 | User intention analysis method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115687618A true CN115687618A (en) | 2023-02-03 |
Family
ID=85066716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211264226.3A Withdrawn CN115687618A (en) | 2022-10-17 | 2022-10-17 | User intention analysis method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115687618A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117558393A (en) * | 2024-01-12 | 2024-02-13 | 成都市龙泉驿区中医医院 | Anorectal patient information arrangement method and system based on artificial intelligence |
-
2022
- 2022-10-17 CN CN202211264226.3A patent/CN115687618A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117558393A (en) * | 2024-01-12 | 2024-02-13 | 成都市龙泉驿区中医医院 | Anorectal patient information arrangement method and system based on artificial intelligence |
| CN117558393B (en) * | 2024-01-12 | 2024-03-19 | 成都市龙泉驿区中医医院 | Anorectal patient information arrangement method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106709024B (en) | Method and device for tracing data table based on blood margin analysis | |
| CN110674360B (en) | Tracing method and system for data | |
| CN114168747A (en) | Knowledge base construction method and system based on cloud service | |
| CN113378554B (en) | Intelligent interaction method and system for medical information | |
| CN115687618A (en) | User intention analysis method and system based on artificial intelligence | |
| CN115757370A (en) | User information communication method and system based on Internet of things | |
| CN114661994B (en) | User interest data processing method and system based on artificial intelligence and cloud platform | |
| CN116756525A (en) | Rock-soil body parameter intelligent testing method and system based on artificial intelligence | |
| CN116204681A (en) | Short video release information detection method, system and cloud platform | |
| CN114329116B (en) | Artificial intelligence-based intelligent park resource matching degree analysis method and system | |
| CN115187191A (en) | Scientific research project progress monitoring method and system based on teaching centralized control management | |
| CN114691830B (en) | Network security analysis method and system based on big data | |
| CN113342864B (en) | Method, system and device for monitoring heat productivity of electronic equipment | |
| CN113645063B (en) | Intelligent data integration method and system based on edge calculation | |
| CN113626559B (en) | Semantic-based intelligent network document retrieval method and system | |
| CN114168670B (en) | Industrial ecological big data integration method and system and cloud platform | |
| CN115455070A (en) | Data management and control method and system for current signals | |
| CN113610117A (en) | Underwater sensing data processing method and system based on depth data | |
| CN114281815A (en) | Industrial innovation resource data analysis method and system | |
| CN114329209A (en) | Image analysis method and system combining innovative resource data | |
| CN114863585A (en) | Intelligent vehicle test monitoring system and method and cloud platform | |
| CN116468534A (en) | Credit information level analysis method and system for collective economic organization | |
| CN113611426A (en) | Mobile medical data pairing method and system | |
| CN116486269A (en) | Bridge crack identification method and system based on image analysis | |
| CN114780645A (en) | Data classification processing method and system based on artificial intelligence and cloud platform |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230203 |
|
| WW01 | Invention patent application withdrawn after publication |