Visual intelligent data mining method and system based on big data

Abstract

The visual intelligent data mining method and system based on big data provided by the present application, for the first visual intelligent information clusters of several business conversation items to be mined, firstly, locates the visual intelligent information whose multi-dimensional constraint conditions meet the specified multi-dimensional constraint conditions in many first visual intelligent information clusters, that is, at least one group of second visual intelligent information; then, analyzes the global description of each business conversation item to be mined in at least one group of second visual intelligent information. In this way, by analyzing the global description of the business conversation items through the visual intelligent information collected within the specified multi-dimensional constraint conditions, it is possible to effectively determine the global description of the business conversation items to be mined in as many second visual intelligent information as possible, thereby improving the quality and credibility of the conversation interest mining of as many visual intelligent information as possible.

Description

Technical Field

[0001] The present application relates to the field of visual data mining technology, and more specifically, to a visual intelligent data mining method and system based on big data. Background Art

[0002] With the recent development of computer technology and the Internet, the term big data has increasingly entered our field of vision, and the rapid development of big data has also been affecting our lives all the time. Nowadays, the application field of big data mining technology is becoming more and more extensive, from the initial text data to visual data. However, in the actual application process, the inventors found that how to ensure efficient and reliable mining of visual intelligent information is a technical problem that needs to be overcome at present. Summary of the invention

[0003] In view of this, the present application provides a visual intelligent data mining method and system based on big data.

[0004] In a first aspect, a visual intelligent data mining method based on big data is provided, which is applied to an intelligent data mining system, and the method comprises:

[0005] Determine a first visual intelligent information cluster of a plurality of business session items to be mined within the multi-dimensional constraint conditions with differences; and determine, in the first visual intelligent information cluster, at least one set of second visual intelligent information whose multi-dimensional constraint conditions meet the specified multi-dimensional constraint conditions;

[0006] Determine a session interest mining result of the to-be-mined business session items in the at least one set of second visual intelligent information.

[0007] In an independently implemented embodiment, determining the session interest mining results of the business session items to be mined in the at least one set of second visual intelligent information includes:

[0008] Determining semantic keywords and derived conversation descriptions of the plurality of business conversation items to be mined by means of a specified semantic feature set;

[0009] In the at least one set of second visualized intelligent information, a first quantitative statistical result of the to-be-mined business conversation item of each semantic keyword and a second quantitative statistical result of the to-be-mined business conversation item of each derived conversation description are determined.

[0010] In an independently implemented embodiment, determining the first quantitative statistical result of the business conversation items to be mined for each semantic keyword in the at least one set of second visualized intelligent information includes:

[0011] Performing differential analysis on the at least one set of second visualized intelligent information by using the semantic keywords of the plurality of business conversation items to be mined, to obtain multiple sets of semantic visualized intelligent information;

[0012] Determine the quantitative statistical results of the business conversation items to be mined included in each group of semantic visualization intelligent information as the first quantitative statistical results.

[0013] In an independently implemented embodiment, in the at least one set of second visualized intelligent information, the second quantitative statistical result of the to-be-mined business session item of each derived session description includes:

[0014] Performing differential analysis on the at least one set of second visualized intelligent information through the derived session descriptions of the plurality of business session items to be mined, to obtain multiple sets of derived visualized intelligent information;

[0015] Determine the quantitative statistical results of the to-be-mined business conversation items included in each group of derived visual intelligent information as the second quantitative statistical results.

[0016] In an independently implemented embodiment, the determining of a first visualized intelligent information cluster of a plurality of business session items to be mined within the multi-dimensional constraint conditions having differences includes:

[0017] Acquire the conversation interaction operation contents of the plurality of business conversation items to be mined within the multi-dimensional constraint conditions with differences;

[0018] A first visualized intelligent information cluster of the conversation description relationship network covering each business conversation item to be mined within the different multi-dimensional constraints is determined through the conversation interaction operation contents of the plurality of business conversation items to be mined.

[0019] In an independently implemented embodiment, determining, through the conversation interaction operation contents of the plurality of business conversation items to be mined, a first visualized intelligent information cluster of a conversation description relationship network covering each business conversation item to be mined within the multi-dimensional constraint conditions with differences includes:

[0020] Performing session description relationship network translation on the session interaction operation content pointing to the same business session item to be mined, to obtain multiple session description relationship networks; wherein the session description relationship network units in each session description relationship network correspond to the same business session item to be mined;

[0021] By using the semantic label and semantic keyword of each of the business session items to be mined, mining the session description relationship network corresponding to each of the business session items to be mined, and obtaining the mined session description relationship network of each of the business session items to be mined;

[0022] The first visualized intelligent information cluster is determined through the mined session description relationship network of the plurality of business session items to be mined.

[0023] In an independent implementation example, the conversation interaction operation content pointing to the same business conversation item to be mined is translated into a conversation description relationship network to obtain multiple conversation description relationship networks, including:

[0024] Performing feature analysis on the conversation interaction operation content pointing to the same business conversation item to be mined, and obtaining a plurality of conversation interaction operation contents; wherein each conversation interaction operation content corresponds to the same business conversation item to be mined;

[0025] Each group of conversation interaction operation contents in any conversation interaction operation content is used as a conversation description relationship network unit to form a conversation description relationship network of the business conversation item to be mined belonging to any conversation interaction operation content, so as to obtain the plurality of conversation description relationship networks.

[0026] In an independently implemented embodiment, the multidimensional constraint condition includes: a timing constraint and a distribution constraint, and the determining, in the first visual intelligent information cluster, of at least one set of second visual intelligent information whose multidimensional constraint condition meets the specified multidimensional constraint condition includes:

[0027] In the first visual intelligent information cluster, determining that the collection period is within the specified timing constraint and is not less than one set of third visual intelligent information;

[0028] In the at least one set of third visual intelligence information, it is determined that the distribution constraint of the information collection thread of the visual intelligence information is within the at least one set of second visual intelligence information of the specified constraint condition set.

[0029] In an independently implemented embodiment, when the conversation interest mining result includes a first quantitative statistical result of the business conversation items to be mined for each semantic keyword and a second quantitative statistical result of the business conversation items to be mined for each derived conversation description, after determining the conversation interest mining result of the business conversation items to be mined in the at least one set of second visual intelligent information, the method further includes:

[0030] Among the first quantitative statistical results corresponding to the plurality of semantic keywords and the second quantitative statistical results corresponding to the plurality of derived conversation descriptions, respectively determine a target first quantitative statistical result and a target second quantitative statistical result whose quantitative statistical results are in the first X; wherein X is an integer not less than 1;

[0031] The target first quantitative statistical result and semantic keywords corresponding to the target first quantitative statistical result, and the target second quantitative statistical result and derived conversation descriptions corresponding to the target second quantitative statistical result are determined.

[0032] In a second aspect, a visual intelligent data mining system based on big data is provided, characterized in that it includes a processor and a memory that communicate with each other, and the processor is used to read a computer program from the memory and execute it to implement the above method.

[0033] The visual intelligent data mining method and system based on big data provided by the embodiment of the present application, for the first visual intelligent information clusters of several business conversation items to be mined, firstly, locates the visual intelligent information whose multi-dimensional constraint conditions meet the specified multi-dimensional constraint conditions in many first visual intelligent information clusters, that is, at least one group of second visual intelligent information; then, analyzes the global description of each business conversation item to be mined in at least one group of second visual intelligent information. In this way, by analyzing the global description of the business conversation items through the visual intelligent information collected within the specified multi-dimensional constraint conditions, it is possible to effectively determine the global description of the business conversation items to be mined in as many second visual intelligent information as possible, thereby improving the quality and credibility of the conversation interest mining of as many visual intelligent information as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 A flowchart of a visual intelligent data mining method based on big data provided in an embodiment of the present application.

[0036] Figure 2 A block diagram of a visual intelligent data mining device based on big data provided in an embodiment of the present application.

[0037] Figure 3 An architectural diagram of a visual intelligent data mining system based on big data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0039] See also Figure 1 , shows a visual intelligent data mining method based on big data, which may include the technical solutions described in steps 100 and 200.

[0040] Step 100, determining a first visual intelligent information cluster of several business session items to be mined within multi-dimensional constraints with differences; in the first visual intelligent information cluster, determining at least one set of second visual intelligent information whose multi-dimensional constraints meet the specified multi-dimensional constraints.

[0041] Step 200: Determine the session interest mining results of the to-be-mined business session items in the at least one set of second visualized intelligent information.

[0042] It can be understood that when executing the contents described in the above steps 100 and 200, for the first visual intelligent information clusters of the business conversation items to be mined, first, the visual intelligent information whose multi-dimensional constraint conditions meet the specified multi-dimensional constraint conditions is located in the many first visual intelligent information clusters, that is, at least one set of second visual intelligent information; then, the global description of each business conversation item to be mined is analyzed in at least one set of second visual intelligent information. In this way, by analyzing the global description of the business conversation items through the visual intelligent information collected within the specified multi-dimensional constraint conditions, the global description of the business conversation items to be mined in as many second visual intelligent information as possible can be effectively determined, thereby improving the quality and credibility of the conversation interest mining of as many visual intelligent information as possible.

[0043] When actually implementing the technical solution, the inventor discovered after long-term analysis that when determining the session interest mining results of the business session items to be mined in the at least one set of second visualization intelligent information, there is a problem of unreliable semantic feature sets, making it difficult to reliably determine the session interest mining results. In order to improve the above technical problems, the step of determining the session interest mining results of the business session items to be mined in the at least one set of second visualization intelligent information described in step 200 may specifically include the contents described in steps 210 and 220.

[0044] Step 210: Determine semantic keywords and derived conversation descriptions of the plurality of business conversation items to be mined by using a specified semantic feature set.

[0045] Step 220 , determining a first quantitative statistical result of the to-be-mined business conversation item of each semantic keyword and a second quantitative statistical result of the to-be-mined business conversation item of each derived conversation description in the at least one set of second visualized intelligent information.

[0046] It can be understood that when executing the contents described in the above steps 210 and 220, when determining the conversation interest mining results of the business conversation items to be mined in the at least one set of second visualization intelligent information, the problem of unreliable semantic feature sets is improved, so that the conversation interest mining results can be reliably determined.

[0047] In this case, in this embodiment, there is a problem of inaccurate semantic keywords in the at least one set of second visual intelligent information, which makes it difficult to accurately determine the first quantitative statistical result of the business conversation items to be mined for each semantic keyword. In order to improve the above technical problem, the step of determining the first quantitative statistical result of the business conversation items to be mined for each semantic keyword in the at least one set of second visual intelligent information described in step 220 can specifically include the contents described in steps 221 and 222.

[0048] Step 221 , performing differential analysis on the at least one set of second visualized intelligent information by using the semantic keywords of the plurality of business conversation items to be mined, to obtain multiple sets of semantic visualized intelligent information.

[0049] Step 222: determine the quantitative statistical results of the business conversation items to be mined included in each group of semantic visualization intelligent information, which are the first quantitative statistical results.

[0050] It can be understood that when executing the contents described in the above steps 221 and 222, in the at least one set of second visualized intelligent information, the problem of inaccurate semantic keywords is improved, so that the first quantitative statistical results of the business conversation items to be mined for each semantic keyword can be accurately determined.

[0051] In this case, in this embodiment, when there is at least one set of second visual intelligent information, there is a problem of inaccurate differential analysis, which makes it difficult to accurately determine the second quantitative statistical results of the business conversation items to be mined for each derived conversation description. In order to improve the above technical problems, the step of determining the second quantitative statistical results of the business conversation items to be mined for each derived conversation description in the at least one set of second visual intelligent information described in step 221 can specifically be performed as described in steps 221a and 221b.

[0052] Step 221a: performing differential analysis on the at least one set of second visualized intelligent information through the derived session descriptions of the plurality of business session items to be mined, to obtain a plurality of sets of derived visualized intelligent information.

[0053] Step 221b: determine the quantitative statistical results of the business session items to be mined included in each group of derived visual intelligent information, which are the second quantitative statistical results.

[0054] It can be understood that when executing the contents described in the above steps 221a and 221b, when there is at least one set of second visualized intelligent information, the problem of inaccurate differential analysis is improved, so that the second quantitative statistical results of the business conversation items to be mined in each derived conversation description can be accurately determined.

[0055] When actually implementing the technical solution, the inventors discovered after long-term analysis that when determining the first visualized intelligent information cluster of several business conversation items to be mined within the multi-dimensional constraints with differences, there is a problem of inaccurate multi-dimensional constraints, making it difficult to accurately determine the first visualized intelligent information cluster. In order to improve the above technical problem, the step of determining the first visualized intelligent information cluster of several business conversation items to be mined within the multi-dimensional constraints with differences described in step 100 may specifically include the contents described in the following steps 110 and 120.

[0056] Step 110: obtaining the conversation interaction operation contents of the plurality of business conversation items to be mined within the different multi-dimensional constraint conditions.

[0057] Step 120 , determining a first visualized intelligent information cluster of a conversation description relationship network covering each business conversation item to be mined within the different multi-dimensional constraints through the conversation interaction operation contents of the plurality of business conversation items to be mined.

[0058] It can be understood that when executing the contents described in the above steps 110 and 120, when determining the first visualized intelligent information cluster of several business session items to be mined within the multi-dimensional constraints with differences, the problem of inaccurate multi-dimensional constraints is improved, so that the first visualized intelligent information cluster can be accurately determined.

[0059] When actually implementing the technical solution, the inventor discovered after long-term analysis that, when using the conversation interaction operation contents of the several business conversation items to be mined, there are multiple problems of inaccurate conversation description relationship networks, which makes it difficult to accurately determine the first visualized intelligent information cluster of the conversation description relationship network covering each business conversation item to be mined within the said different multi-dimensional constraints. In order to improve the above technical problem, the step described in step 120 of determining the first visualized intelligent information cluster of the conversation description relationship network covering each business conversation item to be mined within the said different multi-dimensional constraints through the conversation interaction operation contents of the several business conversation items to be mined can specifically include the contents described in the following steps 121 to 123.

[0060] Step 121 , performing session description relationship network translation on the session interaction operation content pointing to the same business session item to be mined, to obtain multiple session description relationship networks; wherein the session description relationship network units in each session description relationship network correspond to the same business session item to be mined.

[0061] Step 122 , mining the session description relationship network corresponding to each of the business session items to be mined with the help of the semantic tags and semantic keywords of each of the business session items to be mined, and obtaining the mined session description relationship network of each of the business session items to be mined.

[0062] Step 123: determining the first visualized intelligent information cluster through the mined session description relationship network of the plurality of business session items to be mined.

[0063] It can be understood that when executing the contents described in the above steps 121 to 123, the problem of inaccurate conversation description relationship networks is improved through the conversation interaction operation contents of the several business conversation items to be mined, so that the first visualized intelligent information cluster of the conversation description relationship network covering each business conversation item to be mined within the said different multi-dimensional constraints can be accurately determined.

[0064] When actually implementing the technical solution, the inventors discovered after long-term analysis that when translating the conversation description relationship network of the conversation interaction operation content pointing to the same business conversation item to be mined, there is a problem of inaccurate feature analysis, which makes it difficult to accurately obtain multiple conversation description relationship networks. In order to improve the above technical problem, the step of translating the conversation description relationship network of the conversation interaction operation content pointing to the same business conversation item to be mined to obtain multiple conversation description relationship networks described in step 121 can specifically include the contents described in the following steps 121a and 121b.

[0065] Step 121a, performing feature analysis on the conversation interaction operation content pointing to the same business conversation item to be mined, and obtaining a plurality of conversation interaction operation contents; wherein each conversation interaction operation content corresponds to the same business conversation item to be mined.

[0066] Step 121b, taking each group of conversation interaction operation contents in any conversation interaction operation contents as a conversation description relationship network unit, forming a conversation description relationship network of the business conversation items to be mined belonging to any conversation interaction operation contents, so as to obtain the plurality of conversation description relationship networks.

[0067] It can be understood that when executing the contents described in the above steps 121a and 121b, the problem of inaccurate feature analysis is improved when translating the conversation interaction operation contents pointing to the same business conversation item to be mined into a conversation description relationship network, thereby accurately obtaining multiple conversation description relationship networks.

[0068] When actually implementing the technical solution, the inventor discovered after long-term analysis that, in the first visual intelligent information cluster, there is a problem of inaccurate third visual intelligent information, which makes it difficult to accurately determine that the multi-dimensional constraint condition meets the specified multi-dimensional constraint condition and is at least one set of second visual intelligent information. In order to improve the above technical problem, the timing constraints and distribution constraints described in step 100, the step of determining, in the first visual intelligent information cluster, that the multi-dimensional constraint condition meets the specified multi-dimensional constraint condition and is at least one set of second visual intelligent information, can specifically include the contents described in the following steps a1 and a2.

[0069] Step a1: in the first visual intelligent information cluster, determine at least one set of third visual intelligent information whose collection period is within a specified time sequence constraint.

[0070] Step a2: determining, in the at least one set of third visual intelligent information, the at least one set of second visual intelligent information whose distribution constraints of information collection threads of the visual intelligent information are within a specified constraint condition set.

[0071] It can be understood that when executing the contents described in the above steps a1 and a2, when in the first visual intelligent information cluster, the problem of inaccurate third visual intelligent information is improved, so that it is possible to accurately determine that there is at least one set of second visual intelligent information that meets the specified multidimensional constraint conditions.

[0072] Based on the above foundation, when the conversation interest mining results include the first quantitative statistical results of the business conversation items to be mined for each semantic keyword and the second quantitative statistical results of the business conversation items to be mined for each derived conversation description, after determining the conversation interest mining results of the business conversation items to be mined in the at least one set of second visual intelligent information, it may also include the contents described in the following steps s1 and s2.

[0073] Step s1, among the first quantitative statistical results corresponding to a number of semantic keywords and the second quantitative statistical results corresponding to a number of derived conversation descriptions, respectively determine the target first quantitative statistical result and the target second quantitative statistical result whose quantitative statistical results are in the top X; wherein X is an integer not less than 1.

[0074] Step s2, determining the target first quantitative statistical result and the semantic keywords corresponding to the target first quantitative statistical result, and the target second quantitative statistical result and the derived conversation description corresponding to the target second quantitative statistical result.

[0075] It can be understood that when executing the contents described in the above steps s1 and s2, statistics are performed through multiple semantic keywords, thereby improving the accuracy of the derived conversation description.

[0076] Based on the above, please refer to Figure 2 , a visual intelligent data mining device 200 based on big data is provided, which is applied to a visual intelligent data mining system based on big data, and the device comprises:

[0077] The information determination module 210 is used to determine a first visual intelligent information cluster of a plurality of business session items to be mined within the multi-dimensional constraint conditions with differences; in the first visual intelligent information cluster, determine at least one set of second visual intelligent information whose multi-dimensional constraint conditions meet the specified multi-dimensional constraint conditions;

[0078] The result mining module 220 is used to determine the session interest mining results of the to-be-mined business session items in the at least one set of second visual intelligent information.

[0079] Based on the above, please refer to Figure 3 , shows a visual intelligent data mining system 300 based on big data, including a processor 310 and a memory 320 that communicate with each other, and the processor 310 is used to read and execute a computer program from the memory 320 to implement the above method.

[0080] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.

[0081] In summary, based on the above scheme, for the first visual intelligent information clusters of several business conversation items to be mined, first, by locating the visual intelligent information whose multi-dimensional constraint conditions meet the specified multi-dimensional constraint conditions among many first visual intelligent information clusters, that is, at least one set of second visual intelligent information; then, in at least one set of second visual intelligent information, analyze the global description of each business conversation item to be mined. In this way, by analyzing the global description of the business conversation items through the visual intelligent information collected within the specified multi-dimensional constraint conditions, it is possible to effectively determine the global description of the business conversation items to be mined in as many second visual intelligent information as possible, thereby improving the quality and credibility of conversation interest mining for as many visual intelligent information as possible.

[0082] It should be understood that the system and its modules shown above can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above methods and systems can be implemented using computer executable instructions and / or included in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a 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 can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above hardware circuits and software (e.g., firmware).

[0083] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained.

[0084] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0085] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0086] In addition, it will be appreciated by those skilled in the art that various aspects of the present application may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0087] A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0088] The computer program coding required for the operation of each part of the application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program coding can be run completely on the user's computer, or run on the user's computer as an independent software package, or run partly on the user's computer and partly on the remote computer, or run completely on the remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0089] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0090] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0091] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used for the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers allow adaptive changes. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which can be changed according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0092] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in this application are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the content of this application, documents that limit the broadest scope of the claims of this application (currently or later attached to this application) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the attached materials of this application are inconsistent or conflicting with the content described in this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

[0093] Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of the present application. Other variations may also fall within the scope of the present application. Therefore, as an example and not a limitation, the alternative configurations of the embodiments of the present application may be considered to be consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly introduced and described in the present application.

[0094] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A visual intelligent data mining method based on big data, characterized in that: Applied to an intelligent data mining system, the method comprises: Determine a first visual intelligent information cluster of a plurality of business session items to be mined within the multi-dimensional constraint conditions with differences; and determine, in the first visual intelligent information cluster, at least one set of second visual intelligent information whose multi-dimensional constraint conditions meet the specified multi-dimensional constraint conditions; Determine a session interest mining result of the to-be-mined business session items in the at least one set of second visual intelligent information; The multi-dimensional constraint condition includes: a time sequence constraint and a distribution constraint, and the determining of at least one set of second visual intelligent information that meets the multi-dimensional constraint condition in the first visual intelligent information cluster includes: In the first visual intelligent information cluster, determining that the collection period is within the specified timing constraint and is not less than one set of third visual intelligent information; In the at least one set of third visual intelligence information, it is determined that the distribution constraint of the information collection thread of the visual intelligence information is within the at least one set of second visual intelligence information of the specified constraint condition set.

2. The method according to claim 1, characterized in that The determining of the session interest mining results of the to-be-mined business session items in the at least one set of second visual intelligent information includes: Determining semantic keywords and derived conversation descriptions of the plurality of business conversation items to be mined by means of a specified semantic feature set; In the at least one set of second visualized intelligent information, a first quantitative statistical result of the to-be-mined business conversation item of each semantic keyword and a second quantitative statistical result of the to-be-mined business conversation item of each derived conversation description are determined.

3. The method according to claim 2, characterized in that The step of determining the first quantitative statistical result of the business conversation items to be mined for each semantic keyword in the at least one set of second visualized intelligent information includes: By using the semantic keywords of the business conversation items to be mined, performing differential analysis on the at least one set of second visualized intelligent information to obtain multiple sets of semantic visualized intelligent information; Determine the quantitative statistical results of the business conversation items to be mined included in each group of semantic visualization intelligent information as the first quantitative statistical results.

4. The method according to claim 3, characterized in that In the at least one set of second visualized intelligent information, the second quantitative statistical result of the to-be-mined business conversation item of each derived conversation description includes: Performing differential analysis on the at least one set of second visualized intelligent information through the derived session descriptions of the plurality of business session items to be mined, to obtain multiple sets of derived visualized intelligent information; Determine the quantitative statistical results of the business conversation items to be mined included in each group of derived visual intelligent information as the second quantitative statistical results.

5. The method according to claim 1, characterized in that The first visualized intelligent information cluster of several business conversation items to be mined within the multi-dimensional constraint conditions where differences are determined includes: Acquire the conversation interaction operation contents of the plurality of business conversation items to be mined within the multi-dimensional constraint conditions with differences; A first visualized intelligent information cluster of the conversation description relationship network covering each business conversation item to be mined within the different multi-dimensional constraints is determined through the conversation interaction operation contents of the plurality of business conversation items to be mined.

6. The method according to claim 5, characterized in that The determining, through the conversation interaction operation contents of the plurality of business conversation items to be mined, a first visualized intelligent information cluster of the conversation description relationship network covering each business conversation item to be mined within the multi-dimensional constraint conditions with differences comprises: Performing session description relationship network translation on the session interaction operation content pointing to the same business session item to be mined, to obtain multiple session description relationship networks; wherein the session description relationship network units in each session description relationship network correspond to the same business session item to be mined; By using the semantic label and semantic keyword of each of the business session items to be mined, mining the session description relationship network corresponding to each of the business session items to be mined, and obtaining the mined session description relationship network of each of the business session items to be mined; The first visualized intelligent information cluster is determined through the mined session description relationship network of the plurality of business session items to be mined.

7. The method according to claim 6, characterized in that The conversation interaction operation content pointing to the same business conversation item to be mined is translated into a conversation description relationship network to obtain multiple conversation description relationship networks, including: Performing feature analysis on the conversation interaction operation content pointing to the same business conversation item to be mined, and obtaining a plurality of conversation interaction operation contents; wherein each conversation interaction operation content corresponds to the same business conversation item to be mined; Each group of conversation interaction operation contents in any conversation interaction operation content is used as a conversation description relationship network unit to form a conversation description relationship network of the business conversation item to be mined belonging to any conversation interaction operation content, so as to obtain the plurality of conversation description relationship networks.

8. The method according to claim 1, characterized in that In a case where the conversation interest mining result includes a first quantitative statistical result of a business conversation item to be mined for each semantic keyword and a second quantitative statistical result of a business conversation item to be mined for each derived conversation description, after determining the conversation interest mining result of the business conversation item to be mined in the at least one set of second visual intelligent information, the method further includes: Among the first quantitative statistical results corresponding to the plurality of semantic keywords and the second quantitative statistical results corresponding to the plurality of derived conversation descriptions, respectively determine a target first quantitative statistical result and a target second quantitative statistical result whose quantitative statistical results are in the first X; wherein X is an integer not less than 1; The target first quantitative statistical result and semantic keywords corresponding to the target first quantitative statistical result, and the target second quantitative statistical result and derived conversation descriptions corresponding to the target second quantitative statistical result are determined.

9. A visual intelligent data mining system based on big data, characterized in that: The invention comprises a processor and a memory communicating with each other, wherein the processor is used to read a computer program from the memory and execute the computer program to implement the method according to any one of claims 1 to 8.

Images