A knowledge star ball customer retrieval method and system, an electronic device, and a storage medium

Abstract

The application provides a knowledge starball customer retrieval method and system, an electronic device and a storage medium, and the method comprises the following steps: performing knowledge cloud closeness sorting on a knowledge cloud set according to a keyword input by a customer in the knowledge starball; the link relationship between each knowledge cloud in the knowledge cloud set is from the knowledge interaction of the customer; the number of direct links and logical links between each knowledge cloud after sorting is used for adding and sorting the links; the semantic relationship order corresponding to the business document of the corresponding knowledge cloud is used for adding and sorting again; knowledge chain association is performed on the final sorting, and the knowledge of the adjacent knowledge cloud directly or logically linked to the hit knowledge association is automatically queried and returned to the customer; that is, the system used by the customer can change the gravity of the knowledge on each knowledge cloud, so that the knowledge combination of the whole knowledge starball is dynamically changed, the retrieval rule of the customer is continuously adapted, the relevant knowledge clouds are intelligently associated, and the convenient use experience of the knowledge is realized.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of knowledge cloud, and more particularly relates to a knowledge starball customer retrieval method and system, an electronic device, and a storage medium. BACKGROUND

[0002] A conventional search method is to perform text similarity calculation according to a search keyword and knowledge stored in a library, and to perform sorting according to a text similarity calculation result, so as to provide a user with a selection. This method can retrieve many results that are the same as or similar to a user keyword, and can provide the user with more knowledge selection. The conventional search method is convenient for single-knowledge search, but when relevant knowledge is searched, secondary search or manual association is often required for jump, which is not conducive to hierarchical application of associated knowledge. SUMMARY

[0003] Therefore, the application aims to provide a knowledge starball customer retrieval method and system, an electronic device, and a storage medium, which dynamically change the knowledge combination of the entire knowledge starball, continuously adapt to the retrieval rules of customers, intelligently associate relevant knowledge clouds, and realize convenient use experience of knowledge.

[0004] The first aspect of the application discloses a knowledge starball customer retrieval method, which comprises the following steps:

[0005] When a customer uses a system through keyword search of a knowledge starball, knowledge cloud closeness is sorted according to a keyword input by the customer in the knowledge starball to a knowledge cloud set, to obtain a first sorting; wherein a link relationship between each knowledge cloud in the knowledge cloud set comes from knowledge interaction of the customer;

[0006] According to the number of direct links and logical links between each knowledge cloud after sorting, a sorting addition is performed on both sides of the links, to obtain a second sorting;

[0007] According to the keyword, a business document corresponding to a knowledge cloud is retrieved, and a third sorting is obtained by performing a re-addition sorting on the second sorting according to a semantic relationship order in the business document corresponding to each knowledge cloud;

[0008] Knowledge chain association is performed on the third sorting, and knowledge directly or logically linked to adjacent knowledge clouds that hit the knowledge chain association is automatically queried, and the knowledge is assembled and returned to the customer; wherein when the customer selects knowledge other than the current knowledge cloud, the customer is directly jumped to a corresponding knowledge cloud, and knowledge sorting in the knowledge cloud is assembled and provided to the customer for use.

[0009] Optionally, in the knowledge starball customer retrieval method, when the customer uses the keyword search system of the knowledge starball, the closeness of the knowledge cloud is sorted according to the keyword input by the customer in the knowledge starball to the knowledge cloud set, and a first sorting is obtained, including:

[0010] According to the keyword input by the customer in the knowledge starball, the matching degree of each knowledge cloud retrieval input keyword is obtained, and the matching degrees are sorted from high to low to obtain a first sorting.

[0011] Optionally, in the knowledge starball customer retrieval method, the second sorting is obtained by adding the sorting of the direct link and the logical link between the sorted knowledge clouds.

[0012] The number of direct links and logical links between the knowledge clouds is determined.

[0013] According to the number of direct links and logical links between the knowledge clouds, the addition parameters of the connection relationship between the knowledge clouds are determined.

[0014] According to the first sorting and the addition parameters, the knowledge clouds are re-sorted to obtain a second sorting.

[0015] Optionally, in the knowledge starball customer retrieval method, the business document corresponding to the knowledge cloud is retrieved according to the keyword, and the second sorting is re-added and sorted according to the semantic relationship order of the corresponding business document in each knowledge cloud to obtain a third sorting, including:

[0016] The corresponding business document is retrieved in the knowledge cloud according to the keyword; wherein the business document includes the semantics of knowledge.

[0017] The semantic relationship order is obtained by sorting the titles of the corresponding business documents of each knowledge cloud.

[0018] The second sorting is re-added and sorted according to the semantic relationship order to obtain a third sorting.

[0019] Optionally, in the knowledge starball customer retrieval method, before the first sorting is obtained by sorting the closeness of the knowledge cloud according to the keyword input by the customer in the knowledge starball to the knowledge cloud set, it further includes:

[0020] The knowledge cloud is constructed based on the business document, and an initial knowledge cloud set is established.

[0021] Optionally, in the knowledge starball customer retrieval method, the knowledge cloud is constructed based on the business document, and an initial knowledge cloud set is established, including:

[0022] acquire a business document;

[0023] extract a geographical location tag and a business type tag according to the business document;

[0024] classify according to tag information of the geographical location tag and the business type tag;

[0025] set different knowledge clouds for different classifications;

[0026] set an initial closeness and a secondary closeness between knowledge in the knowledge clouds; the initial closeness is a natural closeness between knowledge in the business document or between business documents; the secondary closeness is a correlation relationship established in a knowledge use process or in manual maintenance;

[0027] establish a direct link of each knowledge in a native knowledge cloud and a logical link of each knowledge in other knowledge clouds, so that the knowledge clouds are associated through the direct link and the logical link, and the association dynamically depends on the use of the knowledge and a hot spot of the knowledge.

[0028] Optionally, in the knowledge starball customer retrieval method, after the knowledge cloud construction based on the business document and the establishment of the initial knowledge cloud set, the method further includes:

[0029] updating the gravitational value between knowledge and between knowledge clouds, migrating the knowledge, and constructing the knowledge cloud link.

[0030] The second aspect of the present application discloses a knowledge starball customer retrieval system, comprising:

[0031] a sorting module, configured to, when a customer searches the system through a keyword of the knowledge starball, sort the closeness of the knowledge cloud set according to the keyword input by the customer in the knowledge starball, to obtain a first sorting; sort the link parties according to the number of the direct link and the logical link between the knowledge clouds after the sorting, to obtain a second sorting; and retrieve the business document corresponding to the knowledge cloud according to the keyword, and additionally sort the second sorting according to the order of the semantic relationship in the business document in each knowledge cloud, to obtain a third sorting;

[0032] a return module, configured to, according to the third sorting, associate the knowledge chain, automatically query the knowledge adjacent to the knowledge chain association directly or logically linked, assemble the knowledge, and return the knowledge to the customer; when the customer selects the knowledge outside the current knowledge cloud, the return module directly jumps to the corresponding knowledge cloud and assembles the knowledge sorting in the knowledge cloud to the customer for use.

[0033] The third aspect of the present application discloses an electronic device, comprising:

[0034] one or more processors;

[0035] a storage device having stored thereon one or more programs;

[0036] The one or more programs, when executed by the one or more processors, enable the one or more processors to implement the knowledge sphere customer retrieval method according to any one of the first aspect of the present application.

[0037] The fourth aspect of the present application discloses a storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the knowledge sphere customer retrieval method according to any one of the first aspect of the present application.

[0038] From the above technical solution, the present application provides a knowledge sphere customer retrieval method, which includes: when a customer uses a keyword search system of a knowledge sphere, a first sorting is obtained by sorting the closeness of knowledge clouds in a knowledge cloud set according to a keyword input by the customer in the knowledge sphere; wherein the link relationship between each knowledge cloud in the knowledge cloud set comes from the knowledge interaction of the customer; a second sorting is obtained by adding the sorting of both sides according to the number of direct links and logical links between each knowledge cloud after sorting; a third sorting is obtained by adding the second sorting again according to the semantic relationship order of the business documents corresponding to the knowledge clouds in each knowledge cloud after keyword retrieval; knowledge chain association is performed on the third sorting, and the knowledge of the adjacent knowledge clouds directly or logically linked to the hit knowledge association is automatically queried and returned to the customer after being assembled; wherein when the customer selects knowledge other than the current knowledge cloud, the corresponding knowledge cloud is directly jumped to, and the knowledge sorting inside the knowledge cloud is assembled and provided to the customer for use; that is, when the customer uses the method for retrieval, the knowledge cloud can be quickly jumped to, and the link relationship between the knowledge clouds comes from the knowledge interaction of the customer, the system use of the customer can change the gravitational force of the knowledge on each knowledge cloud, thereby dynamically changing the knowledge combination of the entire knowledge sphere, constantly adapting to the retrieval rule of the customer, intelligently associating the relevant knowledge clouds, and realizing the convenient use experience of the knowledge. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0040] Figure 1 is a flowchart of a knowledge sphere customer retrieval method provided by an embodiment of the present application;

[0041] Figure 2is a flow chart of another knowledge star customer retrieval method provided by an embodiment of the present application;

[0042] Figure 3 is a flow chart of another knowledge star customer retrieval method provided by an embodiment of the present application;

[0043] Figure 4 is a flow chart of another knowledge star customer retrieval method provided by an embodiment of the present application;

[0044] Figure 5 is a flow chart of another knowledge star customer retrieval method provided by an embodiment of the present application;

[0045] Figure 6 is a flow chart of another knowledge star customer retrieval method provided by an embodiment of the present application;

[0046] Figure 7 is a schematic diagram of a knowledge star customer retrieval system provided by an embodiment of the present application;

[0047] Figure 8 is a schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0049] In the present application, the terms “comprising”, “containing” or any other variants thereof are intended to cover non-exclusive containing, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the sentence “including a…” does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0050] The embodiments of the present application provide a knowledge star customer retrieval method, which is used to solve the problem that the conventional search method in the prior art is relatively convenient for searching a single piece of knowledge, but needs secondary search or relies on manual association for jump when searching related knowledge, which is not conducive to hierarchical application of the related knowledge.

[0051] Referring to Figure 1The knowledge starball customer retrieval method comprises the following steps:

[0052] S101, when a customer uses a keyword search system of a knowledge starball, a knowledge cloud closeness degree is sorted according to a keyword input by the customer in the knowledge starball to a knowledge cloud set, and a first sorting is obtained.

[0053] The link relationship between each knowledge cloud in the knowledge cloud set comes from knowledge interaction of the customer.

[0054] It should be noted that when the customer raises a question, the keyword can be determined from the question raised by the customer. The specific way of determining the keyword is not described here, but can be determined according to the actual situation, and is within the protection scope of the present application.

[0055] The keyword input by the customer is calculated to the closeness degree of each knowledge cloud in the knowledge cloud set, and the closeness degree of each knowledge cloud is sorted to obtain the first sorting.

[0056] Each knowledge cloud stores a plurality of knowledge, so the way of determining the closeness degree of the keyword and each knowledge cloud can be to calculate the closeness degree of the keyword and each knowledge cloud in each knowledge cloud, and then calculate the closeness degree of each knowledge cloud.

[0057] Of course, there are other ways to determine the closeness degree of the keyword and each knowledge cloud, which are not described here, but can be determined according to the actual situation, and are within the protection scope of the present application.

[0058] S102, according to the number of direct links and logical links between each knowledge cloud after sorting, the ranking of both sides is added, and the second sorting is obtained.

[0059] The direct link means that a certain knowledge x originally exists in the knowledge cloud A, and the logical link means the reference relationship, which represents the association relationship of other knowledge clouds to the knowledge x.

[0060] It is also worth mentioning that when the knowledge x is cloned and distributed to the associated knowledge cloud, the logical connection disappears automatically.

[0061] One function of the direct link and the logical connection is to enable the knowledge cloud to find the knowledge x.

[0062] Specifically, the more the number of direct links and logical connections, the higher the ranking addition of the knowledge cloud, and vice versa.

[0063] S103, according to the keyword retrieval to the corresponding knowledge cloud business document, and according to the corresponding semantic relationship order in the business document in each knowledge cloud, the second sorting is sorted again, and the third sorting is obtained.

[0064] It should be noted that the key word is a credit card, and the credit card activation, credit card consumption, credit card repayment, credit card cancellation, etc. in different business documents, according to the semantic order relationship, the activation and consumption can only have the repayment and cancellation process. Therefore, the addition parameter of the knowledge cloud storing the corresponding business document is related to the semantics in the business document.

[0065] For example, the search is a credit card, and the credit card activation and credit card consumption are stored in the knowledge cloud C, and the credit card repayment and credit card cancellation are stored in the knowledge cloud A. According to the semantic order relationship, the activation and consumption can only have the repayment and cancellation process, so the knowledge cloud C should be in front of the knowledge cloud A according to the semantic order.

[0066] It should be noted that the second sorting has been determined, and the step is only to perform addition sorting on the basis of the second sorting, and the order may not be changed. Whether the order is changed or not needs to be seen according to the semantic relationship order of each knowledge cloud, which will not be described one by one here, and can be determined according to the actual situation, which is within the protection scope of the present application.

[0067] S104, knowledge chain association is performed on the third sorting, and the knowledge directly or logically linked by the adjacent knowledge cloud hit by automatic query is returned to the customer after being assembled.

[0068] When the customer selects the knowledge outside the current knowledge cloud, the corresponding knowledge cloud is directly jumped to, and the knowledge sorting inside the knowledge cloud is assembled to the customer for use.

[0069] The knowledge assembled and returned to the customer is the result obtained by the final sorting, for example, the knowledge cloud D, C, A and B. The final result is combined with the associated knowledge cloud, for example, the knowledge cloud D is associated with the associated knowledge cloud M and N. When the customer uses the knowledge of the knowledge cloud D, the knowledge M and N can be quickly jumped to.

[0070] Specifically, the knowledge cloud returned to the customer by the third sorting. In the knowledge cloud, the result after the matching degree calculation is knowledge chain associated, the knowledge directly or logically linked by the adjacent knowledge cloud hit by automatic query is returned to the user after being assembled, and the customer selects the knowledge outside the current knowledge cloud. The corresponding knowledge cloud is directly jumped to, and the knowledge sorting inside the knowledge cloud is assembled to the customer for use.

[0071] That is, the knowledge chain association is to find other knowledge clouds with high association degree with the knowledge cloud, and when the knowledge cloud is clicked to view, the related knowledge cloud can be quickly jumped to.

[0072] Therefore, when the customer calls to consult the problem, the knowledge cloud and the jump between the knowledge clouds are used to quickly answer the customer's problem.

[0073] When the customer searches in the knowledge galaxy, the customer can build the association within the knowledge cloud and between the knowledge clouds according to the hit knowledge cloud, simplify the search of the customer, realize the intelligent application of one search for many times, and improve the search experience of the customer.

[0074] In the embodiment, when the customer uses the system by keyword search of the knowledge galaxy, the first sorting is obtained according to the closeness degree sorting of the knowledge cloud set in the knowledge galaxy according to the keyword input by the customer; wherein the link relationship between each knowledge cloud in the knowledge cloud set comes from the knowledge interaction of the customer; the second sorting is obtained by adding the sorting of the link parties according to the number of direct links and logical links between each knowledge cloud after the sorting; the third sorting is obtained by adding the second sorting again according to the order of the corresponding semantic relationship of the business documents in each knowledge cloud according to the business documents corresponding to the knowledge cloud searched by the keyword; the knowledge chain association is performed on the third sorting, the knowledge directly or logically linked with the adjacent knowledge cloud hit by the knowledge association is automatically queried, and the knowledge is assembled and returned to the customer; wherein when the customer selects the knowledge outside the current knowledge cloud, the corresponding knowledge cloud is directly jumped to, and the knowledge sorting within the knowledge cloud is assembled and provided to the customer for use; that is, when the customer uses the method to search, the knowledge can be quickly jumped to the knowledge cloud, the link relationship between the knowledge clouds comes from the knowledge interaction of the customer, the system use of the customer can change the gravity of the knowledge to each knowledge cloud, thereby dynamically changing the knowledge combination of the whole knowledge galaxy, constantly adapting to the search rule of the customer, intelligently associating the related knowledge cloud, and realizing the convenient use experience of the knowledge.

[0075] In actual application, referring to Figure 2 , step S101, when the customer uses the system by keyword search of the knowledge galaxy, the first sorting is obtained according to the closeness degree sorting of the knowledge cloud set in the knowledge galaxy according to the keyword input by the customer, including:

[0076] S201, according to the keyword input by the customer in the knowledge galaxy, the matching degree of each knowledge cloud to the input keyword is obtained, and the matching degrees are sorted from high to low to obtain the first sorting.

[0077] Specifically, when the customer uses the system by keyword search of the knowledge galaxy, the first sorting is obtained according to the closeness degree sorting of the knowledge cloud set in the knowledge galaxy according to the keyword input by the customer; the sorting method is to sort the matching degree of each knowledge cloud to the input keyword from high to low to obtain the first sorting.

[0078] The matching degree is the text similarity between the input keyword and each knowledge in the knowledge cloud.

[0079] Of course, the sorting method can also adopt other methods, which will not be described one by one here, and can be determined according to the actual situation, which is within the protection scope of the application.

[0080] In practical applications, referring to Figure 3 , step S102, the second sorting is obtained by adding the sorting of both sides of the direct link and the number of logical links between the sorted knowledge clouds, including:

[0081] S301, determine the number of direct links and logical links between the knowledge clouds.

[0082] It should be noted that the number of direct links is 1, and the number of logical connections is multiple. Of course, it is also not excluded that the number of direct links is multiple, or the number of logical connections is 1. Here, it is not repeated, and it can be determined according to the actual situation, which is within the protection scope of the present application.

[0083] S302, determine the addition parameter of the connection relationship between the two sides of each knowledge cloud according to the number of direct links and logical links between the knowledge clouds.

[0084] It should be noted that the addition parameter is related to the number of direct links and logical links. Generally, the larger the number is, the larger the addition parameter is, and the smaller the number is, the smaller the addition parameter is.

[0085] The specific process of determining the addition parameter is not repeated here, which can be determined according to the actual situation, which is within the protection scope of the present application.

[0086] S303, re-sort each knowledge cloud according to the first sorting and the addition parameter to obtain the second sorting.

[0087] Specifically, on the basis of the first sorting, the addition parameter of each knowledge cloud is added to the sorting to obtain the second sorting.

[0088] For example, the first sorting is knowledge cloud D, A, B, C; knowledge cloud A and knowledge cloud C have direct link and logical connection relationship, and the number of direct links between knowledge cloud A and knowledge cloud C is 3, and the number of logical connections is 5 times. When the system threshold value is set to be less than 10 times, the matching degree of the sorting at the back is added by 0.01, and the sorting of knowledge cloud D, A, B, C is finally calculated again.

[0089] In practical applications, referring to Figure 4 , step S103, the business document corresponding to the knowledge cloud is retrieved according to the keyword, and the second sorting is added again according to the corresponding semantic relationship order in the business document in each knowledge cloud to obtain the third sorting, including:

[0090] S401, find the corresponding business document in the knowledge cloud by searching the keyword.

[0091] Among them, the business document includes the semantics of knowledge.

[0092] S402, semantic ordering is performed on the titles of the business documents corresponding to the respective knowledge clouds, to obtain a semantic relationship order.

[0093] The knowledge can be stored in different knowledge clouds, for example, credit card activation and credit card consumption are stored in knowledge cloud C, and credit card repayment and credit card cancellation are stored in knowledge cloud A. After searching in the knowledge cloud, the knowledge cloud finds the corresponding business document, and the business document corresponds to the semantic order of the knowledge.

[0094] Finding the corresponding business document can be finding the specific document according to the document ID corresponding to the disassembly.

[0095] S403, the semantic relationship order is added to the second ordering again to obtain a third ordering.

[0096] Finally, according to the corresponding business document of the search question, the result after ordering is finally added according to the semantic relationship order corresponding to each knowledge cloud.

[0097] The semantic order corresponding to the knowledge cloud is related to the search keyword, for example, searching for a credit card, credit card activation and credit card consumption are stored in knowledge cloud C, and credit card repayment and credit card cancellation are stored in knowledge cloud A. According to the semantic order relationship, after activation and consumption, there can be a repayment and cancellation process, so according to the semantic order C, it should be in front of A.

[0098] The semantic relationship order addition adjusts the ordering of the knowledge cloud, for example, the second ordering is knowledge cloud D, A, B, and C. When the customer searches for a credit card, if the matching degree result of knowledge cloud C and knowledge cloud A is not much different, the result is optimized at this time, and the third ordering is knowledge cloud D, C, A, and B.

[0099] In practical application, see Figure 5 In step S101, when the customer searches the keyword using the system of the knowledge star ball, the knowledge cloud closeness degree ordering is performed on the knowledge cloud set according to the keyword input by the customer in the knowledge star ball, to obtain the first ordering, which further includes:

[0100] S501, knowledge cloud construction is performed based on the business document, to establish an initial knowledge cloud set.

[0101] That is, the knowledge cloud set can be constructed in advance, and of course the knowledge cloud set can be updated.

[0102] The connection relationship between the respective knowledge clouds in the initial knowledge cloud set is pre-constructed.

[0103] In the process of interacting with the customer, the link relationship between the respective knowledge clouds can be updated.

[0104] In practical applications, step S501, based on the business document, the knowledge cloud is constructed, and the initial knowledge cloud set is established, including:

[0105] (1) Obtain the business document.

[0106] The business document can include subjects, actions, and specific content, which will not be repeated here, and can be determined according to actual conditions, which are within the protection scope of the present application.

[0107] (2) Extract the geographic location label and the business type label according to the business document.

[0108] Both can be extracted at the same time or in sequence, which will not be repeated here, and can be determined according to actual conditions, which are within the protection scope of the present application.

[0109] Specifically, the extraction rule is to extract according to the template, for example, the rule of the document is "use range: Anhui branch, Beijing branch", at this time, the geographic location label extracted is Anhui branch and Beijing branch.

[0110] The business type label is determined according to the directory level to which the current document belongs, for example, the directory where the current document is located is "channel business-personal online bank-credit card", and according to the template extraction method, the business type label corresponding to the document is credit card.

[0111] (3) Classify according to the label information of the geographic location label and the business type label.

[0112] That is, classify according to the label information of the geographic location label and the label information of the business type label.

[0113] (4) Set different knowledge clouds for different classifications.

[0114] That is, different types of business documents are set to different knowledge clouds. The same type of business document is set to the same knowledge cloud.

[0115] Further, the business document is constructed into multiple knowledge clouds.

[0116] According to the label values such as the above-mentioned label values Anhui branch, Beijing branch, and credit card, the business document is classified, and different knowledge clouds are set for different classifications.

[0117] The knowledge cloud is composed of business documents, and the business document is composed of knowledge. The initial closeness of the knowledge cloud is calculated according to the similarity between the knowledge, the similarity between the knowledge constitutes the closeness between the documents, and finally constitutes the closeness between the knowledge clouds.

[0118] The business document contains multiple knowledge, for example, the credit card business document contains multiple knowledge such as credit card activation, credit card consumption, credit card repayment, and credit card cancellation.

[0119] (5) Set the initial closeness and secondary closeness between knowledge in the knowledge cloud.

[0120] The initial closeness is the natural closeness between knowledge in the business document or between business documents; the secondary closeness is the association relationship established during the use of knowledge or manual maintenance.

[0121] (6) Establish direct links of each knowledge in the original knowledge cloud and logical links of each knowledge in other knowledge clouds, so as to associate the knowledge clouds through the direct links and the logical links, and the association dynamically depends on the use of knowledge and the hot knowledge.

[0122] For different knowledge clouds A and B, if a knowledge x belongs to the knowledge cloud A, when the attraction of the knowledge cloud A to x is less than the attraction of other knowledge clouds to the knowledge x, the knowledge x is divided into other knowledge clouds, and a direct link of the knowledge x to the original knowledge cloud A is established, a logical link of the knowledge x to other knowledge clouds is established, the knowledge clouds are associated through the direct links and the logical links, and the association dynamically depends on the use of knowledge and the hot knowledge.

[0123] It should be noted that for the knowledge cloud, the initial sorting result is the weighted sorting of the frequency and the latest access time of the knowledge.

[0124] The initial sorting result provides a knowledge overview of the current knowledge cloud, that is, the customer can query which is the hot knowledge when clicking the knowledge cloud.

[0125] In practical applications, referring to Figure 6 After the knowledge cloud is constructed based on the business document in step S501 and the initial knowledge cloud set is established, the method further includes:

[0126] S601, update the attraction values between knowledge and between knowledge clouds, migrate the knowledge, and construct the knowledge cloud link.

[0127] The internal knowledge entries and the association relationship between the knowledge clouds are pre-constructed after the customer selects the knowledge cloud.

[0128] When the attraction of two or more knowledge clouds to the knowledge x is greater than the system threshold, the knowledge x is cloned and distributed to each associated knowledge cloud, and the association between the knowledge clouds is cut off, and the false association between the knowledge clouds caused by the special and regular knowledge is weakened.

[0129] The gravity is related to the number of times that the customer uses the knowledge. That is, the system use of the customer can change the gravity of the knowledge to each knowledge cloud. Thus, the knowledge combination of the entire knowledge galaxy is dynamically changed, constantly adapting to the search rule of the customer, intelligently associating relevant knowledge clouds, and realizing the convenient use of knowledge.

[0130] In the embodiment, by constructing the association between knowledge clouds, the customer is facilitated to perform knowledge search, knowledge jump, and knowledge association update, and the convenience of system use is improved. That is, the knowledge cloud of the business type knowledge in the bank can be constructed, when the customer calls to consult a question, the quick answer to the question of the customer is completed based on the knowledge cloud and the jump between knowledge clouds, the association inside the knowledge cloud and between knowledge clouds is dynamically updated, the quick search of the customer is ensured, the automatic relationship between knowledge is dynamically updated, and good use experience is obtained.

[0131] Another embodiment of the application provides a knowledge galaxy customer search system.

[0132] Referring to Figure 7 The knowledge galaxy customer search system comprises:

[0133] The sorting module 101 is configured to, when the customer uses the system through keyword search of the knowledge galaxy, perform knowledge cloud closeness sorting according to the keyword input by the customer in the knowledge galaxy to the knowledge cloud set, to obtain a first sorting; perform sorting addition to both sides of the direct link and the logical link between the sorted knowledge clouds according to the number of the direct link and the logical link, to obtain a second sorting; and search the business document corresponding to the knowledge cloud according to the keyword, and perform again sorting addition to the second sorting according to the semantic relationship order in the business document corresponding to each knowledge cloud, to obtain a third sorting.

[0134] The return module 102 is configured to perform knowledge chain association to the third sorting, automatically query the knowledge directly or logically linked to the adjacent knowledge cloud of the knowledge chain association, assemble the knowledge, and return the knowledge to the customer; when the customer selects the knowledge other than the current knowledge cloud, directly jump to the corresponding knowledge cloud, and assemble the knowledge sorting inside the knowledge cloud to the customer for use.

[0135] The specific working process and principle of each module are described in detail in the knowledge galaxy customer search method provided in the above embodiment, and will not be repeated here. The actual situation can be determined, and it is within the protection scope of the application.

[0136] In the embodiment, the ranking module 101 ranks the knowledge clouds in the knowledge cloud set according to the keywords input by the customer when the customer uses the system through keyword search of the knowledge sphere, to obtain a first ranking; the link relationship between the knowledge clouds in the knowledge cloud set is from the knowledge interaction of the customer; the number of direct links and logical links between the ranked knowledge clouds is added to the ranking of the two parties of the links, to obtain a second ranking; and the business documents corresponding to the knowledge clouds are retrieved according to the keywords, and the second ranking is added again according to the order of the semantic relationship in the business documents in the knowledge clouds, to obtain a third ranking; the returning module 102 associates the knowledge chain according to the third ranking, automatically queries the knowledge directly or logically linked to the adjacent knowledge clouds of the hit knowledge association, assembles the knowledge and returns it to the customer; when the customer selects the knowledge outside the current knowledge cloud, the customer is directly jumped to the corresponding knowledge cloud, and the knowledge ranking in the knowledge cloud is assembled and returned to the customer for use; that is, when the customer uses the method for retrieval, the customer can quickly jump to the knowledge cloud, and the link relationship between the knowledge clouds is from the knowledge interaction of the customer, the system use of the customer can change the attraction of the knowledge to each knowledge cloud, thereby dynamically changing the knowledge combination of the entire knowledge sphere, constantly adapting to the retrieval rule of the customer, intelligently associating the relevant knowledge clouds, and achieving convenient use experience of the knowledge.

[0137] Another embodiment of the present application provides a storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the knowledge sphere customer retrieval method of any one of the above embodiments.

[0138] In the context of the present disclosure, the machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples of the machine-readable storage medium can include one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0139] It should be noted that the computer readable medium in the above disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, an RF (radio frequency) or the like, or any suitable combination of the above.

[0140] The computer readable medium described above can be contained in the electronic device described above; or can exist separately and not be assembled into the electronic device.

[0141] Another embodiment of the present application provides an electronic device, such as Figure 8 as shown, comprising:

[0142] one or more processors 201.

[0143] a storage device 202 having one or more programs stored thereon.

[0144] When the one or more programs are executed by the one or more processors 201, the one or more processors 201 implement the knowledge sphere client retrieval method of any one of the above embodiments.

[0145] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program in accordance with embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for executing the methods illustrated by the flowcharts.

[0146] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

[0147] While several inventive embodiments have been described above, it should be understood that many modifications, additions and deletions can be made to the embodiments, and combinations of components and functions from one embodiment can be combined in other embodiments, while still falling within the scope of the disclosure. Accordingly, the above description is not intended to limit the scope of the disclosure.

[0148] The above description is merely illustrative of the exemplary embodiments of the present disclosure and the principles of the technology involved. It is understood that the scope of the disclosure is not limited to the specific combinations of technical features described above, but also covers other technical solutions formed by any combination of the technical features described above or equivalent features, without departing from the concept disclosed above. For example, the above-described features can be replaced with technical features disclosed in the present disclosure (but not limited to) having similar functions to form technical solutions.

[0149] It should be noted that the knowledge star customer retrieval method and system, electronic device, and storage medium provided by the present application can be used in the fields of artificial intelligence, block chain, distribution, cloud computing, big data, Internet of Things, mobile Internet, network security, chips, virtual reality, augmented reality, holographic technology, quantum computing, quantum communication, quantum measurement, digital twin, or finance. The above are only examples and do not limit the application field of the knowledge star customer retrieval method and system, electronic device, and storage medium provided by the present application.

[0150] The features described in the various embodiments in the specification can be substituted or combined with each other, and the same or similar parts among the various embodiments can be referred to each other, and each embodiment focuses on the difference from other embodiments. Especially, for the system or system embodiments, since they are basically similar to the method embodiments, they are described more simply, and the relevant parts can be referred to the part of the method embodiments. The above described system and system embodiments are only illustrative, and the units described as separate components can be or can not be physically separated, and the components shown as units can be or can not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiments according to the actual needs. Those skilled in the art can understand and implement without creative labor.

[0151] The skilled in the art can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware, computer software or combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in the above description in general. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. The skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0152] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A knowledge sphere client search method, characterized in that, The application comprises: Based on business documents, knowledge cloud construction is carried out to establish an initial knowledge cloud set; When a customer uses the system through keyword search of the knowledge star, the closeness of the knowledge cloud set is sorted according to the keyword input by the customer in the knowledge star, and a first sorting is obtained; wherein the link relationship between each knowledge cloud in the knowledge cloud set comes from the knowledge interaction of the customer; According to the number of direct links and logical links between each knowledge cloud after sorting, the sorting addition of the link parties is carried out, and a second sorting is obtained; According to the business documents corresponding to the knowledge cloud retrieved by the keyword, the second sorting is sorted again according to the semantic relationship order in the business documents of each knowledge cloud, and a third sorting is obtained; The third sorting is associated with the knowledge chain, the knowledge directly or logically linked to the adjacent knowledge cloud of the knowledge chain association is automatically queried, and the knowledge is assembled and returned to the customer; wherein when the customer selects the knowledge outside the current knowledge cloud, the corresponding knowledge cloud is directly jumped to, and the knowledge sorting inside the knowledge cloud is assembled and provided to the customer for use.

2. The knowledge sphere client search method according to claim 1, characterized in that, When the customer uses the system through keyword search of the knowledge star, the closeness of the knowledge cloud set is sorted according to the keyword input by the customer in the knowledge star, and a first sorting is obtained, which comprises: According to the keyword input by the customer in the knowledge star, the matching degree of each knowledge cloud searching the input keyword is obtained, and the matching degrees are sorted from high to low to obtain a first sorting.

3. The knowledge sphere client search method according to claim 1, wherein, According to the number of direct links and logical links between each knowledge cloud after sorting, the sorting addition of the link parties is carried out, and a second sorting is obtained, which comprises: The number of direct links and logical links between each knowledge cloud is determined; According to the number of direct links and logical links between each knowledge cloud, the addition parameters of the connection relationship parties possessed by each knowledge cloud are determined; According to the first sorting and the addition parameters, each knowledge cloud is re-sorted to obtain a second sorting.

4. The knowledge sphere client search method according to claim 1, wherein, According to the keyword, the business documents corresponding to the knowledge cloud are retrieved, and the second sorting is sorted again according to the semantic relationship order in the business documents of each knowledge cloud to obtain a third sorting, which comprises: The keyword is searched in the knowledge cloud to find the corresponding business documents; wherein the business documents comprise the semantics of knowledge; The semantic relationship order is obtained by performing semantic sorting on the titles of the business documents corresponding to each knowledge cloud; The second sorting is sorted again according to the semantic relationship order to obtain a third sorting.

5. The knowledge sphere client search method according to claim 1, wherein, Based on business documents, knowledge cloud construction is carried out to establish an initial knowledge cloud set, which comprises: Obtaining business documents; Extracting geographical location tags and business type tags from the business documents; Classifying according to the tag information of the geographical location tags and the business type tags; Different knowledge clouds are set for different classifications; The initial closeness and the secondary closeness between knowledge are set between the knowledge clouds; wherein the initial closeness is the natural closeness between knowledge in the business documents or between the business documents; the secondary closeness is the association relationship established in the knowledge use process or manual maintenance; The direct link of each knowledge in the original knowledge cloud and the logical link of each knowledge in other knowledge clouds are established, so that the knowledge clouds are associated through the direct link and the logical link, and the association is dynamically dependent on the use of the knowledge and the hot spot of the knowledge.

6. The knowledge sphere client search method of claim 1, wherein, After the knowledge cloud construction based on the business document and the establishment of the initial knowledge cloud set, the method further comprises: updating the gravity value between the knowledge and the knowledge cloud, migrating the knowledge, and constructing the knowledge cloud link.

7. A knowledge sphere client search system, characterized by, The method comprises: constructing the knowledge cloud based on the business document and establishing the initial knowledge cloud set; The sorting module is configured to, when a customer searches the system through the keyword of the knowledge star ball, sort the knowledge cloud closeness degree of the customer input keyword to the knowledge cloud set in the knowledge star ball to obtain a first sorting; According to the number of the direct link and the logical link between the sorted knowledge clouds, the link parties are sorted with addition, to obtain a second sorting; and according to the keyword retrieval to the corresponding business document of the knowledge cloud, and according to the corresponding semantic relationship order in the business document of each knowledge cloud, the second sorting is sorted with addition again to obtain a third sorting; The returning module sorts the knowledge chain association of the third sorting, automatically queries the adjacent knowledge cloud direct or logical link knowledge of the knowledge chain association hit, assembles the knowledge and returns it to the customer; wherein, when the customer selects the knowledge outside the current knowledge cloud, the corresponding knowledge cloud is directly jumped to, and the knowledge sorting inside the knowledge cloud is assembled to the customer for use.

8. An electronic device, comprising: The method comprises: one or more processors; a storage device having stored thereon one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the knowledge star ball customer retrieval method according to any one of claims 1-6.

9. A storage medium, characterized by The computer program is stored on the storage device and is executed by the processor to implement the knowledge star ball customer retrieval method according to any one of claims 1-6.

Images