Method and device for obtaining association relationship between knowledge points

Abstract

The embodiment of the present application provides a method and device for obtaining the association relationship between knowledge points. In the method, a query log is obtained, the query log includes query statements input by multiple users and the knowledge points corresponding to the query statements; multiple query combinations are obtained from the query log, the query combination includes a user identifier and the knowledge points corresponding to the multiple query statements input by the user with the user identifier; multiple knowledge points with a co-occurrence frequency greater than or equal to a first threshold are obtained from the multiple query combinations; and the association relationship between multiple knowledge points is constructed. So that the knowledge points are no longer isolated. Therefore, during the user query process, if a certain knowledge point is hit, a link to the knowledge point with the association relationship can be displayed. If the user needs to view the knowledge point with the association relationship, the user can directly click on the corresponding link without searching again, so the number of user searches is reduced, and the search time and complexity of the search are reduced.

Description

Technical Field

[0001] The present application relates to the field of database technology, and more specifically, to a method and device for obtaining association relationships between knowledge points. Background Art

[0002] Based on the query statement input by the user, the knowledge base can be searched for knowledge points that match the query statement; currently, the user may need to search multiple times, that is, input different query statements multiple times to search the knowledge base for multiple knowledge points required by the user.

[0003] During the process of realizing the creativity of the present invention, the applicant discovered that since the knowledge points in the knowledge base are relatively isolated, it takes a long time for users to retrieve the multiple knowledge points they need from the knowledge base. Based on this, how to make the knowledge points contained in the knowledge base not isolated is a difficult problem that technical personnel in this field urgently need to solve. Summary of the invention

[0004] In view of this, the present application provides a method and device for acquiring association relationships between knowledge points.

[0005] This application provides the following technical solutions:

[0006] According to a first aspect of an embodiment of the present disclosure, a method for acquiring association relationships between knowledge points is provided, including:

[0007] Acquire a query log, wherein the query log includes query statements respectively input by multiple users and knowledge points corresponding to the query statements; the knowledge points corresponding to the query statements are knowledge points that meet preset conditions in the query results corresponding to the query statements;

[0008] Obtaining multiple query combinations from the query log, the query combinations including a user identifier and knowledge points corresponding to multiple query statements input by a user having the user identifier;

[0009] Obtaining, from the plurality of query combinations, a plurality of knowledge points whose co-occurrence frequency is greater than or equal to a first threshold, wherein at least two of the plurality of knowledge points correspond to different query statements;

[0010] Establish association relationships between the multiple knowledge points.

[0011] According to a second aspect of an embodiment of the present disclosure, there is provided a device for acquiring association relationships between knowledge points, including:

[0012] A first acquisition module is used to acquire a query log, wherein the query log includes query statements respectively input by multiple users and knowledge points corresponding to the query statements; the knowledge points corresponding to the query statements are knowledge points that meet preset conditions in the query results corresponding to the query statements;

[0013] A second acquisition module is used to obtain multiple query combinations from the query log, where the query combination includes a user identifier and knowledge points corresponding to multiple query statements input by a user having the user identifier;

[0014] A third acquisition module is used to obtain a plurality of knowledge points whose co-occurrence frequency is greater than or equal to a first threshold from a plurality of query combinations, wherein at least two of the plurality of knowledge points correspond to different query statements;

[0015] The construction module is used to construct the association relationship between the multiple knowledge points.

[0016] According to a third aspect of an embodiment of the present disclosure, a server is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the knowledge point query method as described in the first aspect.

[0017] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the storage medium are executed by a processor of a server, the server is enabled to execute the method for acquiring association relationships between knowledge points as described in the first aspect.

[0018] According to the fifth aspect of the embodiment of the present disclosure, a computer program product is provided, which can be directly loaded into the internal memory of a computer, such as the memory included in the server described in the third aspect above, and contains software code. After being loaded and executed by a computer, the computer program can implement the method for obtaining the association relationship between knowledge points as described in the first aspect.

[0019] Through the above technical solution, it can be known that in the method for obtaining the association relationship between knowledge points provided by the present application, a query log is obtained, the query log includes query statements input by multiple users and the knowledge points corresponding to the query statements; the knowledge points corresponding to the query statements are the knowledge points that meet the preset conditions in the query results corresponding to the query statements; multiple query combinations are obtained from the query log, the query combinations include user identifiers and knowledge points corresponding to multiple query statements input by users with the user identifiers; multiple knowledge points with a co-occurrence frequency greater than or equal to a first threshold are obtained from the multiple query combinations, and at least two of the multiple knowledge points correspond to different query statements; and the association relationship between the multiple knowledge points is constructed. Thus, the association relationship between multiple knowledge points is established, so that the knowledge points are no longer isolated. Thus, in the user query process, if a certain knowledge point is hit, the link of the knowledge point with the association relationship can be displayed. If the user needs to view the knowledge point with the association relationship, the corresponding link can be directly clicked without re-searching, so the number of user searches is reduced, and the search time and the complexity of the search are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0021] Figure 1 A structural diagram of the hardware architecture involved in the embodiments of the present application;

[0022] Figure 2 A flowchart of a method for obtaining association relationships between knowledge points provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of the relationship between the interface for displaying the knowledge text and the interface for displaying the question and answer area provided in an embodiment of the present application;

[0024] Figure 4 A structural diagram of a device for acquiring association relationships between knowledge points provided in an embodiment of the present application;

[0025] Figure 5 The invention is a block diagram showing a device for a server according to an exemplary embodiment. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] The embodiments of the present application provide a method and device for obtaining the association relationship between knowledge points. Before introducing the technical solution provided by the embodiments of the present application, the relevant technologies and hardware architecture involved in the embodiments of the present application are first described.

[0028] First, the relevant technologies involved in the embodiments of the present application are introduced.

[0029] In the related art, the knowledge base includes multiple knowledge points.

[0030] Exemplarily, multiple knowledge points are obtained by splitting the source document. The source documents corresponding to different knowledge points may be the same or different.

[0031] For example, the source document includes 10 paragraphs. Exemplarily, the source text is divided into 10 knowledge points, that is, each paragraph corresponds to one knowledge point; exemplary, the source document is divided into 5 knowledge points, and one knowledge point includes one or more paragraphs in the source document; exemplary, the source document is divided into 20 knowledge points, and one knowledge point includes one or more sentences in a paragraph.

[0032] Exemplarily, the knowledge point includes a source document; exemplary, the knowledge point is obtained based on other knowledge points.

[0033] Exemplarily, there are many ways to represent knowledge points, and the present application embodiment provides but is not limited to: any one of a linked list, an array, a structure, and a table. The structure of a knowledge point is described below using a table as an example.

[0034] Exemplarily, the structure of knowledge points in the related art is shown in Table 1.

[0035] Table 1 Structure of knowledge points in related technologies

[0036]

[0037] Exemplarily, the body of the knowledge includes any one of the knowledge title and the knowledge content; Exemplarily, the knowledge content corresponds to the knowledge title. For example, the knowledge content corresponding to the knowledge title "Deposit Period of Bank of China Fortune Personal Notice Deposits" may be: Regardless of the actual deposit period, personal notice deposits are divided into two types: 1-day notice deposits and 7-day notice deposits according to the length of the depositor's advance notice. 1-day notice deposits must notify the agreed withdrawal of deposits 1 day in advance, while 7-day notice deposits must notify the agreed withdrawal of deposits 7 days in advance. For 1-day notice deposits and 7-day notice deposits, customers must come to the counter 1 day or 7 days in advance to make an appointment for withdrawal registration. The so-called transfer means that the system can automatically transfer the principal and interest to the customer's current account on the due date, but the customer is required to come to the counter every cycle (7 days) to handle the agreed transfer business.

[0038] Illustratively, the business directory included in the knowledge point may include one-level or multiple-level directories. Table 1 is described by taking the example that the business directory includes two-level directories.

[0039] Exemplarily, the business directory included in the knowledge point is used to indicate the storage path of the knowledge text included in the knowledge point. Exemplarily, the business directory included in the knowledge point is the name of the storage device storing the knowledge point and / or the name of the folder.

[0040] Exemplarily, the knowledge title can be obtained from the knowledge content text based on natural language processing technology; exemplary, the knowledge title can be obtained from the source document.

[0041] Exemplarily, the graph tags contained in the knowledge point refer to the attribute information of the knowledge text. Exemplarily, the graph tags include: product (the product described by the content of the knowledge text), bank (which branch or which head office the content of the knowledge text is aimed at), customer type. Exemplarily, customer types include but are not limited to: individual customers, wealth management customers, ordinary customers, private banking customers, BOC wealth management customers, etc.

[0042] Exemplarily, the personalized tags contained in the knowledge points are added by human agents, and the human agents can mark the knowledge points based on their own understanding of the knowledge points. For example, the human agent with the identification A of the human agent in Table 1 marked "Fuden's special time deposit". Next time, the human agent with the identification A of the human agent can accurately search for the knowledge points shown in Table 1 based on the query statement "Fuden's special time deposit".

[0043] It should be noted that sometimes when a human agent searches for a required knowledge point, but the human agent has some understanding of the knowledge point or has his own habit of naming the knowledge point, then the human agent can add his own understanding to the personalized label of the knowledge point. In this way, the thinking habits of different human agents can be taken into account, and the annotation of knowledge can be enriched, thereby speeding up the efficiency of knowledge query and improving the accuracy of knowledge query.

[0044] For example, for the same knowledge point, the personalized tags marked by different manual agents may be different or the same; because the manual agent needs to log in before searching for knowledge points, the query statement of the manual agent includes the identification of the manual agent. Therefore, in the process of retrieving knowledge points by personalized tags, it will not be affected by the personalized tags marked by other manual agents.

[0045] Exemplarily, the management attributes included in the knowledge point refer to information about the administrator who manages the knowledge point. For example, the management attributes include the department to which the administrator belongs and the user group to which the administrator belongs.

[0046] The structure of the knowledge points in Table 1 is only an example and does not limit the structure of the knowledge points. For example, the knowledge points may include: business catalog, knowledge text, graph label, personal label, one or more fields in management attributes.

[0047] Exemplarily, the knowledge point also includes a receiving group, and the receiving group includes identifiers of users who can query and obtain the knowledge point.

[0048] In the related art, the keywords in the query statement may include keywords belonging to one or more fields of the business catalog, knowledge text, graph label, personal label, and management attribute. In the process of retrieving knowledge points whose relevance to the query statement is greater than or equal to the third threshold from the knowledge base, the relevance between the query statement and one or more of the business catalog, knowledge text, graph label, personal label, and management attribute contained in the knowledge point may be obtained to obtain the knowledge point whose relevance to the query statement is greater than or equal to the third threshold, so that the client can display the link to the knowledge point whose relevance to the query statement is greater than or equal to the third threshold.

[0049] If the user needs to view a certain knowledge point, he clicks on the link of the corresponding knowledge point, so that the knowledge text contained in the knowledge point can be displayed. However, if the user needs to view other knowledge points related to the knowledge point, he needs to search again, resulting in more search times and longer search time.

[0050] Secondly, the hardware architecture involved in the embodiments of the present application is described.

[0051] like Figure 1As shown, it is a structural diagram of the hardware architecture involved in the embodiment of the present application, and the hardware architecture includes: an electronic device 11, a server 12 and a knowledge base 13.

[0052] Exemplarily, the electronic device 11 can be any electronic product that can interact with a user through one or more methods such as a keyboard, touchpad, touch screen, remote control, voice interaction or handwriting device, such as a mobile phone, a laptop computer, a tablet computer, a PDA, a personal computer, a wearable device, a smart TV, a PAD, etc.

[0053] Exemplarily, the server 12 may be a single server, or a server cluster consisting of multiple servers, or a cloud computing server center. The server 12 may include a processor, a memory, a network interface, and the like.

[0054] It should be noted that Figure 1 This is just an example. There are many types of electronic devices, not limited to Figure 1 Computers in the.

[0055] Exemplarily, the electronic device 11 may establish a connection and communicate with the server 12 via a wireless network or a wired network.

[0056] Exemplarily, the knowledge base 13 may establish a connection and communicate with the server 12 via a wireless network or a wired network.

[0057] Exemplarily, the user may input a query statement through the electronic device 11. The electronic device 11 may send the query statement to the server 12. The electronic device 11 may display the query result fed back by the server 12. The user may operate the link of the knowledge point in the query result through the electronic device 11, for example, by clicking; the electronic device 11 may display the link click operation of the response knowledge point fed back by the server 12, and the knowledge text of the knowledge point fed back. The user may browse the knowledge text contained in the knowledge point through the electronic device 11.

[0058] In summary, the server 12 can obtain query statements corresponding to multiple users, query times of the multiple query statements, query results corresponding to the multiple query statements, and user operations on knowledge points in the query results.

[0059] Exemplarily, the user may be a human agent or a customer.

[0060] Exemplarily, the user may input a query statement through a user interface of a client displayed by the electronic device 11 , and the client may be an application client or a web client.

[0061] The server 12 is used to execute the method for obtaining the association relationship between knowledge points provided in the embodiment of the present application, and interact with the knowledge base 13.

[0062] Exemplarily, the knowledge base 13 storing knowledge points may be located in the server 12 , or the knowledge base 13 may be independent of the server 12 .

[0063] Those skilled in the art should understand that the above-mentioned electronic devices and servers are only examples, and other existing or future electronic devices or servers that are applicable to the present disclosure should also be included in the scope of protection of the present application and are incorporated herein by reference.

[0064] The following describes a method for obtaining association relationships between knowledge points provided in an embodiment of the present application in combination with hardware architecture and related technologies.

[0065] like Figure 2 FIG. 1 is a flowchart of a method for obtaining association relationships between knowledge points provided in an embodiment of the present application. The method can be applied to Figure 1 In the server shown, the method comprises steps S21 to S24 during implementation.

[0066] Step S21: obtaining a query log, wherein the query log includes query statements respectively input by multiple users and knowledge points corresponding to the query statements; the knowledge points corresponding to the query statements are knowledge points that meet preset conditions in the query results corresponding to the query statements.

[0067] Exemplarily, the query results may include links to one or more knowledge points; the preset conditions in “knowledge points in the query results that meet the preset conditions” may include at least one of the following: the link of the knowledge point is clicked by the user, the time for which the knowledge text of the knowledge point is browsed by the user is greater than or equal to threshold A, and the number of times the link of the knowledge point is opened is greater than or equal to threshold B.

[0068] The following is an example of the preset condition that the link of the knowledge point is clicked by the user. For example, the query statement is the provident fund application process, if the query results include: the link of the introduction of housing provident fund loans, the link of the housing provident fund application process, the link of the housing provident fund loan guarantee, the link of the housing provident fund loan approval, the link of the housing provident fund loan issuance, and the link of the housing provident fund loan inquiry, if the user clicks the link of the housing provident fund application process, then the knowledge point "housing provident fund application process" meets the preset condition, if the user does not click the link of other knowledge points, then other knowledge points do not meet the preset condition.

[0069] Exemplarily, for the same query statement, the number of knowledge points that meet the preset conditions in the query results corresponding to the query statement may be one or more.

[0070] Step S22: obtaining a plurality of query combinations from the query log, wherein the query combinations include a user identifier and knowledge points corresponding to a plurality of query statements input by a user having the user identifier.

[0071] Exemplarily, the user needs to log in before querying, and the user identifier can be a user account. Exemplarily, if the user does not log in before querying, the user identifier can be a device identifier of an electronic device used by the user.

[0072] There are many ways to implement step S22, and the embodiments of the present application provide but are not limited to the following two.

[0073] The first implementation method of step S22 includes the following steps A11 to A12.

[0074] Step A11: Obtain query statements corresponding to a plurality of user identifiers and knowledge points corresponding to the query statements from the query log.

[0075] Step A12: Classify the knowledge points corresponding to the query statements corresponding to the same user identifier into the same query combination.

[0076] For example, if the following contents are obtained from the query log: user ID 1, query statement A input by user ID 1, query statement B input by user ID 1, knowledge point A1 corresponding to query statement A, and knowledge point A2, knowledge point B1 corresponding to query statement B; user ID 2, query statement C input by user ID 2, query statement D input by user ID 2, knowledge point C1 corresponding to query statement C, and knowledge point D1 corresponding to query statement D. Then, two query combinations can be obtained, namely: {user ID 1, knowledge point A1 corresponding to query statement A, knowledge point A2 corresponding to query statement A, knowledge point B1 corresponding to query statement B}, {user ID 2, knowledge point C1 corresponding to query statement C, knowledge point D1 corresponding to query statement D}.

[0077] The second implementation method of step S22 includes the following steps A21 to A22.

[0078] Step A21: For any user identifier, the query time of multiple query statements input by the user with the user identifier is obtained from the query log.

[0079] In an optional implementation, the query time of all query statements input by the user having the user identifier may be obtained from the query log.

[0080] In an optional implementation, since the user's query requirements are constantly changing, for any user identifier, step A21 can obtain from the query log the query time of multiple query statements input by the user with the user identifier within a preset time period.

[0081] Exemplarily, the end time of the preset time period is the current time, and the start time is the current time + the preset time period. As time passes, the end time and the start time of the preset time period are constantly changing.

[0082] Step A22: grouping the knowledge points corresponding to the multiple query statements whose query time difference is less than or equal to the set time into the same query combination.

[0083] Exemplarily, the number of query combinations corresponding to the same user identifier may be one or more.

[0084] For example, the setting time may be determined based on actual conditions and is not limited here.

[0085] Exemplarily, if the following contents are obtained from the query log: user ID 1, query statement A entered by user ID 1 at query time 1, query statement B entered by user ID 1 at query time 2, knowledge point A1 corresponding to query statement A and knowledge point A2, knowledge point B1 corresponding to query statement B; user ID 2, query statement C entered by user ID 2 at query time 3, query statement D entered by user ID 2 at query time 4, query statement E entered by user ID 2 at query time 5, knowledge point C1 corresponding to query statement C, knowledge point D1 corresponding to query statement D, and knowledge point E1 corresponding to query statement E.

[0086] If the difference between query time 1 and query time 2 is less than or equal to the set time, then the knowledge point A1 corresponding to query statement A, the knowledge point A2 corresponding to query statement A, and the knowledge point B1 corresponding to query statement B can be divided into the same query combination, for example, the query combination {user identifier 1, knowledge point A1 corresponding to query statement A, knowledge point A2 corresponding to query statement A, knowledge point B1 corresponding to query statement B} is obtained. If query time 3 is earlier than query time 4 and earlier than query time 5, and the difference between query time 3 and query time 4 is greater than the set time, but the difference between query time 4 and query time 5 is less than or equal to the set time, then the knowledge point D1 corresponding to query statement D and the knowledge point E1 corresponding to query statement E can be divided into the same query combination, for example, the query combination {user identifier 2, knowledge point D1 corresponding to query statement D, knowledge point E1 corresponding to query statement E} is obtained.

[0087] Since the query combination includes at least two knowledge points corresponding to the query statements, the knowledge point C1 corresponding to the query statement C cannot form a query combination by itself.

[0088] It can be understood that if the query time interval between two query statements is smaller, the correlation between the two query statements may be greater. Based on this, in an embodiment of the present application, the knowledge points corresponding to multiple query statements whose query time difference is less than or equal to the set time are divided into the same query combination.

[0089] Step S23: obtaining a plurality of knowledge points whose co-occurrence frequency is greater than or equal to a first threshold from a plurality of query combinations, wherein at least two of the plurality of knowledge points correspond to different query statements.

[0090] In an optional implementation, the co-occurrence frequency = the number of query combinations containing the multiple knowledge points / the number of all query combinations.

[0091] For example, step S22 obtains 100,000 query combinations from the query log, of which 80,000 query combinations include knowledge point A and knowledge point B, and the co-occurrence frequency of knowledge point A and knowledge point B = 80,000 / 100,000.

[0092] In an optional implementation, the co-occurrence frequency = the number of user identifiers corresponding to the query combination containing the multiple knowledge points / the number of user identifiers corresponding to all query combinations.

[0093] For example, step S22 obtains 100,000 query combinations from the query log, and the 100,000 query combinations correspond to 90,000 user identifications, that is, some user identifications correspond to multiple query combinations, among which 80,000 query combinations include knowledge point A and knowledge point B. These 80,000 query combinations correspond to 70,000 user identifications, then the co-occurrence frequency of knowledge point A and knowledge point B = 70,000 / 90,000.

[0094] Step S24: construct association relationships between the multiple knowledge points.

[0095] In an optional implementation, the association relationships among the multiple knowledge points are not in order. For example, if knowledge point A, knowledge point B, and knowledge point C are associated with each other, then the knowledge points associated with knowledge point A are knowledge point B and knowledge point C. The knowledge points associated with knowledge point B are knowledge point A and knowledge point C.

[0096] In an optional implementation, the association relationship between the multiple knowledge points has an order, and the process of determining the association relationship includes steps B11 and B12.

[0097] Step B11: determining a viewing order representing a user's need to view the multiple knowledge points based on the query times of the query statements corresponding to the multiple knowledge points in the multiple query combinations.

[0098] Exemplarily, for each query combination, the multiple knowledge points included in the query combination are sorted from early to late according to the query time of the query statements corresponding to the knowledge points, so as to obtain the sorting order of the multiple knowledge points corresponding to the query combination.

[0099] Exemplarily, if the multiple knowledge points are knowledge point A, knowledge point B and knowledge point C, if a query combination contains a query statement corresponding to knowledge point A whose query time is time 1, a query statement corresponding to knowledge point B whose query time is time 2, and a query statement corresponding to knowledge point C whose query time is time 3, and time 1 is later than time 2 and later than time 3, then the sorting order of knowledge point A, knowledge point B and knowledge point C is: knowledge point C, knowledge point B, knowledge point A.

[0100] It is understandable that the sorting order of the multiple knowledge points corresponding to each query combination may be different or the same. If the sorting order of the multiple knowledge points corresponding to each query combination is the same, the viewing order is the sorting order. If the sorting order of the multiple knowledge points corresponding to each query combination is not exactly the same, but the sorting order of the multiple knowledge points corresponding to a large number of query combinations is the same, the sorting order of the multiple knowledge points corresponding to a large number of query combinations shall be the viewing order.

[0101] Step B12: establishing association relationships among the plurality of knowledge points based on the viewing order.

[0102] For example, if multiple knowledge points with associated relationships are: knowledge point A, knowledge point B, and knowledge point C, and the viewing order of the three knowledge points is: knowledge point C, knowledge point B, knowledge point A. Then, the knowledge points with associated relationships with knowledge point C are: knowledge point B, knowledge point A; the knowledge points with associated relationships with knowledge point B are: knowledge point C, knowledge point A; and the knowledge points with associated relationships with knowledge point A are: knowledge point C, knowledge point B.

[0103] In the method for obtaining the association relationship between knowledge points provided in the embodiment of the present application, a query log is obtained, the query log includes query statements input by multiple users and the knowledge points corresponding to the query statements; the knowledge points corresponding to the query statements are the knowledge points that meet the preset conditions in the query results corresponding to the query statements; multiple query combinations are obtained from the query log, the query combinations include user identifiers and the knowledge points corresponding to the multiple query statements input by users with the user identifiers; multiple knowledge points with a co-occurrence frequency greater than or equal to a first threshold are obtained from the multiple query combinations, at least two of the multiple knowledge points correspond to different query statements; and the association relationship between the multiple knowledge points is constructed. Thus, the association relationship between the multiple knowledge points is established, so that the knowledge points are no longer isolated. Thus, in the user query process, if a certain knowledge point is hit, the link of the knowledge point with the association relationship can be displayed, and if the user needs to view the knowledge point with the association relationship, the corresponding link can be directly clicked without re-searching, so the number of user searches is reduced, and the search time and the complexity of the search are reduced.

[0104] In an optional implementation, a knowledge point includes a knowledge text, the location of the knowledge text in a source document, a first identifier, and a second identifier; the first identifier is an identifier of a knowledge point corresponding to a previous knowledge text in the source document located at the knowledge text; the second identifier is an identifier of a knowledge point corresponding to a next knowledge text in the source document located at the knowledge text; the source document is divided into multiple knowledge texts. The method for obtaining association relationships between the knowledge points also includes: for any of the knowledge points, adding a first association identifier of a knowledge point having the association relationship with the knowledge point to the knowledge point; the knowledge text contained in the knowledge point having the first association identifier and the knowledge text contained in the knowledge point belong to different source documents.

[0105] In the embodiment of the present application, for each knowledge point, the identifier of the knowledge point having the association relationship with the knowledge point is called the first association identifier.

[0106] The structure of the knowledge points in the embodiments of the present application is different from the structure of the knowledge points in the related art.

[0107] Exemplarily, there are many ways to represent knowledge points, and the embodiments of the present application provide but are not limited to: any one of a linked list, an array, a structure, and a table. The structure of a knowledge point is illustrated below using a table as an example. Exemplarily, the structure of a knowledge point in the embodiments of the present application is shown in Table 2.

[0108] Table 2 Structure of knowledge points in the embodiments of this application

[0109]

[0110]

[0111] Exemplarily, there are multiple ways to represent the identification of knowledge points, such as the first identification and the second identification, for example, using one or more of letters, numbers, and special symbols. Table 2 uses the first identification and the second identification represented by numbers as an example for explanation.

[0112] Exemplarily, the identifier of a knowledge point may be randomly assigned, and different knowledge points may have different identifiers; exemplary, the identifier of a knowledge point is related to the position of the knowledge text contained in the knowledge point in the source document.

[0113] For example, the 3rd, 4th and 5th paragraphs contained in the source document correspond to a knowledge point respectively, and the knowledge point shown in Table 2 corresponds to the 4th paragraph contained in the source document, so the "position in the source document" is 4; exemplarily, the source document context index includes a first identifier and a second identifier, as shown in Table 2, the first identifier is 3 and the second identifier is 5.

[0114] Exemplarily, a knowledge point may include one or more first identifiers. If a knowledge point includes a first identifier, exemplarily, the first identifier is an identifier of a knowledge point corresponding to any previous knowledge text located in the knowledge text contained in the knowledge point in the source document. Take the example that each paragraph contained in the source document corresponds to a knowledge point. If knowledge point A corresponds to the first paragraph of the source document, knowledge point B corresponds to the second paragraph of the source document, knowledge point C corresponds to the third paragraph of the source document, knowledge point D corresponds to the fourth paragraph of the source document, and knowledge point E corresponds to the fifth paragraph of the source document, then the first identifier contained in knowledge point C can be the identifier of knowledge point B or the identifier of knowledge point A. Exemplarily, the first identifier is an identifier of a knowledge point corresponding to an adjacent previous knowledge text located in the knowledge text contained in the knowledge point in the source document. For example, the first identifier contained in knowledge point C is the identifier of knowledge point B.

[0115] If knowledge point E includes multiple first identifiers, the knowledge texts contained in the knowledge points with multiple first identifiers are adjacent in the source document, and are adjacent to the knowledge texts contained in knowledge point E; for example, the multiple first identifiers contained in knowledge point E are: the identifier of knowledge point D and the identifier of knowledge point C.

[0116] If knowledge point E includes multiple first identifiers, the knowledge texts contained in the knowledge points with multiple first identifiers may not be adjacent in the source document. For example, the multiple first identifiers contained in knowledge point E are: the identifier of knowledge point C and the identifier of knowledge point A.

[0117] Exemplarily, the number of the second identifiers included in the knowledge point may be one or more. The description of the second identifier can refer to the first identifier, which will not be repeated here.

[0118] Exemplarily, the knowledge point also includes: at least one of an identification ID of a source document and a name of the source document.

[0119] In summary, the knowledge points provided in the embodiments of the present application include the source document context index (i.e., the first identifier and the second identifier), so that multiple knowledge points from the same source document are associated. The knowledge points provided in the embodiments of the present application include the association relationship identifier ID, so that multiple knowledge points from different source documents are associated.

[0120] Exemplarily, the number of first association identifiers included in a knowledge point may be one or more. Exemplarily, if the number of first association identifiers included in a knowledge point is multiple, if the association relationship is obtained based on the viewing order, exemplary, the multiple first association identifiers included in the knowledge point are stored in sequence according to the viewing order. As shown in Table 2, the viewing order is: knowledge points with first association identifier 1, knowledge points with first association identifier 2, and knowledge points with first association identifier 3.

[0121] In an optional implementation, during the query process, the user can obtain the query result based on the query statement, and the client can display the link of the knowledge point contained in the query result; the server responds to the operation of clicking the link of knowledge point A, obtains the first identifier and the second identifier contained in the knowledge point A; and sends the knowledge text contained in the knowledge point A, the knowledge text contained in the knowledge point with the first identifier, and the knowledge text contained in the knowledge point with the second identifier to the client. When displaying, the client not only displays the knowledge text contained in the knowledge point A, but also displays the knowledge text contained in the knowledge point with the first identifier and the knowledge text contained in the knowledge point with the second identifier. Therefore, if the user still needs to view the previous knowledge text or the next knowledge text of the knowledge text contained in the knowledge point A, there is no need to search again, which reduces the number of searches, reduces the search time, reduces the complexity of the search, and makes the user search faster.

[0122] Exemplarily, a document is generated based on the knowledge text included in the knowledge point, the knowledge text included in the knowledge point with the first identifier, and the knowledge text included in the knowledge point with the second identifier, and the document is sent to the client.

[0123] The knowledge text contained in the knowledge point, the knowledge text contained in the knowledge point with the first identifier, and the knowledge text contained in the knowledge point with the second identifier are all derived from the same source document. Exemplarily, different knowledge texts belonging to the same source document may have a logical order association, and the logical order association is the order in which users browse the knowledge texts. For example, 6 knowledge points are split from the source document, among which the positions of the knowledge texts contained in the 6 knowledge points in the source document are: knowledge 1, knowledge point 2, knowledge point 3, knowledge point 4, knowledge point 5, knowledge point 6; the knowledge texts contained in knowledge 1, knowledge point 2, knowledge point 3, knowledge point 4, knowledge point 5, and knowledge point 6 are: introduction to housing provident fund loans, housing provident fund application process, housing provident fund loan guarantee, housing provident fund loan approval, housing provident fund loan issuance, housing provident fund loan inquiry. That is, the knowledge texts contained in the 6 knowledge points are semantically associated.

[0124] Exemplarily, the knowledge texts of the knowledge points in the document including the knowledge texts included in the knowledge point, the knowledge texts included in the knowledge point with the first identifier, and the knowledge texts included in the knowledge point with the second identifier are sorted in a logical order.

[0125] The user may need to view the "Introduction to Housing Provident Fund Loans" included in Knowledge Point 1, the "Housing Provident Fund Application Process" included in Knowledge Point 2, and the "Housing Provident Fund Loan Guarantee" included in Knowledge Point 3 in sequence. Through the embodiment of the present application, it is only necessary to search once, and after obtaining Knowledge Point 2, the knowledge texts included in the above three knowledge points can be viewed. If the relevant technology is used, it is necessary to search three times to view the knowledge texts included in the above three knowledge points.

[0126] The process of obtaining knowledge points stored in the knowledge base is described below. The process of obtaining knowledge points includes the following steps C11 to C13.

[0127] Step C11: Split the source document into multiple knowledge texts.

[0128] Exemplarily, the source document may be a file in various formats, such as a txt file, a word file, a PPT file, an excel file, etc.

[0129] There are many ways to split the source document. The embodiments of the present application provide but are not limited to the following two.

[0130] The implementation method of the first step C11 includes: obtaining multiple knowledge texts from the source document according to the knowledge splitting template.

[0131] Exemplarily, the knowledge splitting template can be pre-set according to the requirements. Different types of knowledge texts correspond to different knowledge splitting templates, so as to improve the efficiency of obtaining knowledge points and obtain a knowledge base.

[0132] Exemplarily, the knowledge splitting template may be in the form of an array, a table, a linked list, etc. Exemplarily, the knowledge splitting template includes one or more fields in the business directory, knowledge text, location in the source document, source document identification ID, source document context index, graph label, personality label, and management attribute shown in Table 2. Exemplarily, the knowledge splitting template also includes extraction rules.

[0133] Exemplarily, the extraction rules can be set based on the structure of the source document. For example, the content included in the source document has been set at an outline level, and the extraction rules can be to determine the content with an outline level of main text as knowledge content, and to determine the content that is located in front of the knowledge content and has an outline level of non-main text content (for example, an outline level of 1, 2, or 3) as a knowledge title.

[0134] Exemplarily, the business catalog included in the knowledge point may be the same as the business catalog of the source document.

[0135] Knowledge maintainers and producers propose and establish knowledge needs through knowledge investigation and knowledge inventory, which makes it easier for producers to create knowledge points according to knowledge splitting templates.

[0136] Exemplarily, in the embodiment of the present application, the content with the outline level of non-text is called title, and the content with the outline level of text is called knowledge content.

[0137] The implementation method of the second step C11 includes: based on natural language processing technology, splitting the source document to obtain multiple knowledge texts.

[0138] Exemplarily, the relevance between multiple paragraphs in the source document is calculated, and paragraphs with a relevance greater than or equal to a threshold A are determined as one knowledge text; and different paragraphs with a relevance less than the threshold A are determined as different knowledge texts.

[0139] Exemplarily, the relevance between multiple sentences in the source document is calculated, and sentences with a relevance greater than or equal to a threshold A are determined as one knowledge text; different sentences with a relevance less than the threshold A are determined as different knowledge texts.

[0140] Step C12: assigning identifiers to the plurality of knowledge texts.

[0141] Exemplarily, an identifier may be randomly assigned to the knowledge text, and the identifier is the identifier of the knowledge point that contains the knowledge text.

[0142] Exemplarily, the identifier of the knowledge point containing the knowledge text may be determined based on the location of the knowledge text in the source document.

[0143] Step C13: Based on the positions of the multiple knowledge texts in the source document, determine the first identifiers and the second identifiers respectively corresponding to the multiple knowledge texts to form knowledge points respectively corresponding to the multiple knowledge texts.

[0144] In an optional implementation, the knowledge point further includes a second association identifier associated with the knowledge point. The number of the second association identifiers associated with the knowledge point included in the knowledge point may be one or more.

[0145] In an embodiment of the present application, for any knowledge point, a knowledge point that has a high relevance to the knowledge point and contains knowledge texts that do not belong to the same source document as the knowledge text contained in the knowledge point is called an associated knowledge point. The specific step of obtaining the second associated identifier of the associated knowledge point includes: for each knowledge point, obtaining an associated knowledge point whose relevance to the knowledge point is greater than or equal to a second threshold, and the knowledge text contained in the associated knowledge point and the knowledge text contained in the knowledge point belong to different source documents. Wherein, the knowledge point includes the second associated identifier of the associated knowledge point.

[0146] Exemplarily, the second threshold may be determined based on actual conditions and is not limited here.

[0147] In an optional implementation, the process further includes constructing a correspondence between knowledge points and FAQs (Frequently Asked Questions). The process of establishing the correspondence includes steps D11 and D12.

[0148] Step D11: For each of the knowledge points, a question-answer pair is obtained from the knowledge text included in the knowledge point, wherein the question-answer pair includes a question and an answer corresponding to the question, and the answer included in the question-answer pair belongs to the knowledge text.

[0149] Exemplarily, the knowledge text may include questions and answers corresponding to the questions.

[0150] Exemplarily, the questions included in the knowledge text have preset symbols, such as "?", so the questions can be obtained from the knowledge text based on the preset symbols; exemplary, sentences or paragraphs matching the questions can be screened out from the knowledge text as answers.

[0151] Exemplarily, the knowledge text may include answers but not questions; exemplary, a question set may be set in advance, the question set includes multiple questions, and the answers to the questions included in the question set are obtained from the knowledge text.

[0152] Exemplarily, the question and the answer are combined into a question-answer pair.

[0153] Step D12: Constructing a correspondence between the knowledge point and the question-answer pair.

[0154] In summary, illustratively, the knowledge points included in the knowledge base mentioned in the embodiments of the present application include: business directory, knowledge text, location in source document, source document identification ID, source document context index, association relationship identification ID, associated knowledge point ID (i.e., second association identification), map label, personality label, memory label, and at least one of management attributes. This makes it so that the various knowledge points in the knowledge base are no longer isolated, but are associated through one or more of the source document context index, association relationship identification ID, and associated knowledge point ID, so when querying the knowledge points stored in the knowledge base, the query time can be shortened and the number of retrieval times can be reduced.

[0155] The process of searching for knowledge points based on the above-mentioned knowledge base is described below. The knowledge point search method includes the following steps E11 to E14.

[0156] Step E11: receiving a query statement from the client.

[0157] Step E12: Obtain from the knowledge base a plurality of target knowledge points whose relevance to the query statement is greater than or equal to a third threshold.

[0158] Step E13: Sending the links corresponding to the multiple target knowledge points to the client.

[0159] Exemplarily, the client may display links corresponding to multiple target knowledge points respectively; the user may operate, for example, click, the links corresponding to the multiple target knowledge points displayed by the client.

[0160] Step E14: In response to the operation of clicking the link of the first target knowledge point among the multiple target knowledge points fed back by the client, the knowledge text contained in the first target knowledge point and the link of the knowledge point having the association relationship with the first target knowledge point are sent.

[0161] If the user needs to view knowledge points that are associated with the first target knowledge point, there is no need to search again, thereby reducing the number of searches.

[0162] Exemplarily, if a knowledge point contains multiple first association identifiers, and the association relationship is determined based on a viewing order, then the step of sending a link to the knowledge text contained in the first target knowledge point and the knowledge point having the association relationship with the first target knowledge point includes: generating link information based on the viewing order corresponding to the first target knowledge point, and the multiple knowledge points having the association relationship with the first target knowledge point contained in the link information are sorted according to the viewing order corresponding to the first target knowledge point; and sending the link information to the client.

[0163] Since the viewing order represents the order in which users view various knowledge points, displaying the links to the knowledge points that are associated with the first target knowledge point in the viewing order is more in line with the user's viewing logic. Users can view the knowledge points in the order of the links to the displayed knowledge points without manual sorting.

[0164] In an optional implementation, it also includes: in response to the operation of clicking on the link of the first target knowledge point, sending an associated knowledge area to the client; wherein the associated knowledge area includes one or more of a link to a knowledge point with the first associated identifier, a link to a knowledge point with the second associated identifier, a link to a source document to which the knowledge text contained in the knowledge point belongs, and a link to multiple knowledge points obtained by splitting the source document to which the knowledge text contained in the knowledge point belongs.

[0165] The user can click the corresponding link in the associated knowledge area displayed on the client to view the corresponding knowledge.

[0166] In an optional implementation, the following steps F1 to F2 may also be included.

[0167] Step F1: In response to clicking the link of the first target knowledge point, the question-answer pair corresponding to the first target knowledge point, the question-answer pair corresponding to the knowledge point with the first identifier, and the question-answer pair corresponding to the knowledge point with the second identifier are queried from the correspondence between the preset knowledge points and the question-answer pairs.

[0168] In step F1, the first identifier and the second identifier are identifiers included in the first target knowledge point.

[0169] Step F2: Sending a question and answer area to the client, the question and answer area including question and answer pairs corresponding to the knowledge point, question and answer pairs corresponding to the knowledge point with the first identifier, and question and answer pairs corresponding to the knowledge point with the second identifier.

[0170] Exemplarily, the interface for displaying the question and answer area and the interface for displaying the knowledge text may be different areas of the same interface, or different interfaces.

[0171] like Figure 3 The figure is a schematic diagram of the relationship between the interface for displaying the knowledge text and the interface for displaying the question and answer area provided in an embodiment of the present application.

[0172] Figure 3 The middle frame 31 frames the knowledge text, the name of the interface displaying the knowledge text is business introduction, and the name of the interface displaying the question and answer area is frequently asked questions.

[0173] In an optional implementation, the following steps G1 to G4 are also included.

[0174] Step G1: Based on the knowledge point, the knowledge point with the first identifier and the knowledge point with the second identifier, generate navigation identifier information, the navigation identifier information including a first navigation identifier corresponding to the knowledge text contained in the knowledge point, a second navigation identifier corresponding to the knowledge text contained in the knowledge point with the first identifier, and a third navigation identifier corresponding to the knowledge text contained in the knowledge point with the second identifier.

[0175] Exemplarily, the knowledge title included in the knowledge text may be determined as the navigation identifier of the knowledge text; and a corresponding relationship between the navigation identifier and the knowledge text may be established.

[0176] Step G2: in response to an operation of clicking a target navigation identifier included in the navigation identifier information, sending the navigation identifier information to the client.

[0177] Step G3: receiving a second click operation on the target navigation identifier included in the click navigation identifier information from the client.

[0178] Step G4: In response to the second click operation, controlling the client to display the knowledge text corresponding to the target navigation identifier, where the target navigation identifier is any one of the first navigation identifier, the second navigation identifier and the third navigation identifier.

[0179] Still Figure 3 For example, the content circled in box 32 is navigation identification information; Figure 3 As shown, the navigation information includes: introduction, preferential policies, consultation telephone number, handling outlets and handling procedures; if the user needs to view the preferential policies, he can click on the preferential policies in the navigation information, and the text content corresponding to the preferential policies will automatically scroll. If the user needs to view the consultation telephone number, he can click on the consultation telephone number in the navigation information, and the text content corresponding to the consultation telephone number will automatically scroll.

[0180] In an optional implementation, the knowledge point may also include: one or more of a graph label, a personal label, and a memory label.

[0181] Exemplarily, graph labels can be obtained based on knowledge content analysis.

[0182] Exemplarily, the personalized label is obtained by manual marking by a human agent.

[0183] Exemplarily, the memory tag is obtained by artificial marking by the customer.

[0184] Exemplarily, the memory tag includes the customer's voiceprint, fingerprint, ID number, mobile phone number, and other information that can represent the user's identity.

[0185] For example, it should be noted that when a user searches for a knowledge point in the knowledge base, if the user searches for a corresponding knowledge point, the user's information (such as personal information, voiceprint information, etc.) and the query statement entered by the user during the search are added to the memory tag of the knowledge point. In this way, when the user searches again in the future, the memory tag can be directly used to retrieve the part of the knowledge point, which speeds up the query efficiency of the knowledge point and improves the accuracy of the knowledge point query.

[0186] Exemplarily, the query statement may be content in any format such as pictures, videos, texts, or EXCEL.

[0187] In an optional implementation, the user may add, modify or delete a personal tag or a memory tag at any time, and the personal tag or the memory tag may be updated in real time.

[0188] In an optional implementation, a large number of users' query methods can be obtained from the query log, including querying by personalized tags, querying by memory tags, and querying by graph tags; the potential relationship between multiple query methods is determined based on the query log. For example, if a large number of users use the graph tag query and also use the memory tag query; then, during the process of the user using the graph tag query, the user will be prompted whether to use the memory tag query. Exemplarily, the process of obtaining the potential relationship between different query methods includes the following steps F1 to F3.

[0189] Step F1: Obtain query logs corresponding to multiple users respectively.

[0190] Step F2: obtaining the query methods used by the multiple users within a set time period from the query logs corresponding to the multiple users respectively.

[0191] Exemplarily, the set time period may be determined based on actual conditions and is not limited here, for example, it may be 30 minutes, 1 hour, etc.

[0192] Step F3: If the number of users who use the same at least two query methods within a set time period is greater than or equal to a third threshold, it is determined that the first query method and the second query method have a potential relationship.

[0193] The method is described in detail in the embodiments disclosed in the above-mentioned application. The method of the application can be implemented by various forms of devices. Therefore, the application also discloses a device, and a specific embodiment is given below for detailed description.

[0194] like Figure 4 As shown, it is a structural diagram of a device for acquiring association relationships between knowledge points provided in an embodiment of the present application, the device includes: a first acquisition module 41, a second acquisition module 42, a third acquisition module 43 and a construction module 44, wherein:

[0195] The first acquisition module 41 is used to acquire a query log, wherein the query log includes query statements respectively input by multiple users and knowledge points corresponding to the query statements; the knowledge points corresponding to the query statements are knowledge points that meet preset conditions in the query results corresponding to the query statements;

[0196] A second acquisition module 42 is used to obtain multiple query combinations from the query log, where the query combination includes a user identifier and knowledge points corresponding to multiple query statements input by a user having the user identifier;

[0197] A third acquisition module 43 is used to obtain a plurality of knowledge points whose co-occurrence frequency is greater than or equal to a first threshold from a plurality of query combinations, wherein at least two of the plurality of knowledge points correspond to different query statements;

[0198] The construction module 44 is used to construct the association relationship between the multiple knowledge points.

[0199] In an optional implementation, the second acquisition module includes:

[0200] A first acquisition unit is used to obtain, for any user identifier, from the query log, query times of multiple query statements input by a user having the user identifier;

[0201] The division unit is used to divide the knowledge points corresponding to multiple query statements whose query time difference is less than or equal to the set time into the same query combination.

[0202] In an optional implementation, the building blocks include:

[0203] A first determining unit, configured to determine a viewing order representing that a user needs to view the multiple knowledge points based on query times of query statements corresponding to the multiple knowledge points in the multiple query combinations;

[0204] An establishing unit is used to establish an association relationship between the multiple knowledge points based on the viewing order.

[0205] In an optional implementation, the knowledge point includes a knowledge text, a location of the knowledge text in a source document, a first identifier, and a second identifier; the first identifier is an identifier of a knowledge point corresponding to a previous knowledge text in the source document located at the knowledge text; the second identifier is an identifier of a knowledge point corresponding to a next knowledge text in the source document located at the knowledge text; the source document is split into multiple knowledge texts; and further includes:

[0206] An adding module is used to add, for any of the knowledge points, a first association identifier of a knowledge point having the association relationship with the knowledge point to the knowledge point; the knowledge text contained in the knowledge point having the first association identifier and the knowledge text contained in the knowledge point belong to different source documents.

[0207] In an optional implementation, the method further includes:

[0208] A splitting module, used for splitting the source document to obtain multiple knowledge texts;

[0209] An allocation module, used for allocating identifiers to the plurality of knowledge texts;

[0210] The first determination module is used to determine the first identifiers and the second identifiers respectively corresponding to the multiple knowledge texts based on the positions of the multiple knowledge texts in the source document, so as to form knowledge points respectively corresponding to the multiple knowledge texts.

[0211] In an optional implementation, the method further includes:

[0212] A fourth acquisition module is used to obtain, for each of the knowledge points, an associated knowledge point whose relevance to the knowledge point is greater than or equal to a second threshold, wherein the knowledge text contained in the associated knowledge point and the knowledge text contained in the knowledge point belong to different source documents;

[0213] Wherein, the knowledge point includes a second association identifier of the associated knowledge point.

[0214] In an optional implementation, the knowledge point also includes one or more of a business directory, a graph label, a personal label and a memory label; wherein the business directory is used to indicate the storage path of the knowledge text contained in the knowledge point; the graph label represents the attribute information of the knowledge text contained in the knowledge point; the personal label is the content described by the human agent for the knowledge point, and the memory label includes the customer's identity information and / or the customer's query statement for the knowledge point.

[0215] In an optional implementation, the method further includes:

[0216] A receiving module, used for receiving a query statement from a client;

[0217] A fifth acquisition module, configured to obtain from the knowledge base a plurality of target knowledge points whose relevance to the query statement is greater than or equal to a third threshold;

[0218] A first sending module, used for sending the links corresponding to the multiple target knowledge points to the client;

[0219] The second sending module is used to send the knowledge text contained in the first target knowledge point and the link of the knowledge point having the association relationship with the first target knowledge point in response to the operation of clicking the link of the first target knowledge point among the multiple target knowledge points fed back by the client.

[0220] In an optional implementation, the second sending module also includes: a generating unit, used to generate link information based on the viewing order corresponding to the first target knowledge point, wherein the multiple knowledge points having the association relationship with the first target knowledge point contained in the link information are sorted according to the viewing order corresponding to the first target knowledge point; and a sending unit, used to send the link information to the client.

[0221] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0222] Figure 5 The invention is a block diagram showing a device for a server according to an exemplary embodiment.

[0223] The server includes, but is not limited to, a processor 51 , a memory 52 , a network interface 53 , an I / O controller 54 , and a communication bus 55 .

[0224] It should be noted that those skilled in the art can understand that Figure 5 The server structure shown in the figure does not constitute a limitation on the server, and the server may include Figure 5 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0225] Combine the following Figure 5 A detailed introduction to each component of the server:

[0226] The processor 51 is the control center of the server. It uses various interfaces and lines to connect various parts of the entire server. It executes various functions of the server and processes data by running or executing software programs and / or modules stored in the memory 52, and calling data stored in the memory 52, so as to monitor the server as a whole. The processor 51 may include one or more processing units; illustratively, the processor 51 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 51.

[0227] The processor 51 may be a central processing unit (CPU), or an application specific integrated circuit ASIC (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;

[0228] The memory 52 may include a memory, such as a high-speed random access memory (RAM) 521 and a read-only memory (ROM) 522, and may also include a large-capacity storage device 523, such as at least one disk storage, etc. Of course, the server may also include hardware required for other services.

[0229] The memory 52 is used to store instructions executable by the processor 51. The processor 51 has the following functions: obtaining a query log, the query log including query statements input by multiple users and knowledge points corresponding to the query statements; the knowledge points corresponding to the query statements are knowledge points that meet preset conditions in the query results corresponding to the query statements;

[0230] Obtaining multiple query combinations from the query log, the query combinations including a user identifier and knowledge points corresponding to multiple query statements input by a user having the user identifier;

[0231] Obtaining, from the plurality of query combinations, a plurality of knowledge points whose co-occurrence frequency is greater than or equal to a first threshold, wherein at least two of the plurality of knowledge points correspond to different query statements;

[0232] Establish association relationships between the multiple knowledge points.

[0233] A wired or wireless network interface 53 is configured to connect the server to the network.

[0234] The processor 51, the memory 52, the network interface 53 and the I / O controller 54 can be interconnected via a communication bus 55, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0235] In an exemplary embodiment, the server may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned method for acquiring the association relationship between knowledge points.

[0236] In an exemplary embodiment, the present disclosure provides a storage medium including instructions, such as a memory 52 including instructions, and the instructions can be executed by a processor 51 of a server to complete the above method. Optionally, the storage medium can be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0237] In an exemplary embodiment, a computer-readable storage medium is also provided, which can be directly loaded into the internal memory of a computer, such as the above-mentioned memory 52, and contains software code. After being loaded and executed by a computer, the computer program can implement the steps shown in any embodiment of the method for obtaining the association relationship between the above-mentioned knowledge points.

[0238] In an exemplary embodiment, a computer program product is also provided, which can be directly loaded into the internal memory of a computer, such as the memory contained in the server, and contains software code. After being loaded and executed by a computer, the computer program can implement the steps shown in any embodiment of the method for obtaining the association relationship between knowledge points described above.

[0239] It should be noted that the features described in the various embodiments in this specification can be replaced or combined with each other. For the device or system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0240] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0241] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0242] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may 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 method for obtaining association relationships between knowledge points. It is characterized in that include: Acquire a query log, wherein the query log includes query statements respectively input by multiple users and knowledge points corresponding to the query statements; The knowledge point corresponding to the query statement is a knowledge point that satisfies a preset condition in the query result corresponding to the query statement; Obtaining multiple query combinations from the query log, the query combinations including a user identifier and knowledge points corresponding to multiple query statements input by a user having the user identifier; Obtaining, from the plurality of query combinations, a plurality of knowledge points whose co-occurrence frequency is greater than or equal to a first threshold, wherein at least two of the plurality of knowledge points correspond to different query statements; Constructing association relationships between the multiple knowledge points; The knowledge point includes a knowledge text, a location of the knowledge text in a source document, a first identifier, and a second identifier; the first identifier is an identifier of a knowledge point corresponding to a previous knowledge text in the source document located at the knowledge text; The second identifier is an identifier of a knowledge point corresponding to the next knowledge text located in the source document of the knowledge text; The source document is split into multiple knowledge texts; The method for acquiring the association relationship between knowledge points also includes: For any of the knowledge points, adding a first association identifier of a knowledge point having the association relationship with the knowledge point to the knowledge point; The knowledge text included in the knowledge point having the first association identifier and the knowledge text included in the knowledge point belong to different source documents.

2. According to the method for obtaining the association relationship between knowledge points according to claim 1, It is characterized in that The step of obtaining multiple query combinations from the query log comprises: For any user identifier, obtaining query times of multiple query statements input by a user having the user identifier from the query log; The knowledge points corresponding to multiple query statements whose query time difference is less than or equal to the set time are divided into the same query combination.

3. According to the method for obtaining the association relationship between knowledge points according to claim 2, It is characterized in that The step of constructing the association relationship of the plurality of knowledge points comprises: Determining a viewing order representing that a user needs to view the multiple knowledge points based on query times of query statements corresponding to the multiple knowledge points in the multiple query combinations; Based on the viewing order, an association relationship between the multiple knowledge points is established.

4. According to the method for obtaining the association relationship between knowledge points according to claim 1, It is characterized in that The process of acquiring the knowledge points includes: Splitting the source document to obtain multiple knowledge texts; assigning identifiers to the plurality of knowledge texts; Based on the positions of the multiple knowledge texts in the source document, the first identifiers and the second identifiers respectively corresponding to the multiple knowledge texts are determined to form knowledge points respectively corresponding to the multiple knowledge texts.

5. According to the method for obtaining the association relationship between knowledge points according to claim 4, It is characterized in that Also includes: For each of the knowledge points, obtaining an associated knowledge point whose relevance to the knowledge point is greater than or equal to a second threshold, wherein the knowledge text contained in the associated knowledge point and the knowledge text contained in the knowledge point belong to different source documents; Wherein, the knowledge point includes a second association identifier of the associated knowledge point.

6. The method for acquiring association relationships between knowledge points according to any one of claims 1, 2, 3, 4 or 5, It is characterized in that The knowledge points also include one or more of a business catalog, a map label, a personal label, and a memory label; Among them, the business directory is used to indicate the storage path of the knowledge text contained in the knowledge point; the graph label represents the attribute information of the knowledge text contained in the knowledge point; the personalized label is the content described by the human agent for the knowledge point, and the memory label includes the customer's identity information and / or the customer's query statement for the knowledge point.

7. The method for acquiring association relationships between knowledge points according to any one of claims 1 to 5, It is characterized in that Also includes: Receive query statements from the client; Acquire from the knowledge base a plurality of target knowledge points whose relevance to the query statement is greater than or equal to a third threshold; Sending links corresponding to the multiple target knowledge points to the client; In response to the operation of clicking the link of a first target knowledge point among the multiple target knowledge points fed back by the client, the knowledge text contained in the first target knowledge point and the link of the knowledge point having the association relationship with the first target knowledge point are sent.

8. According to the method for obtaining the association relationship between knowledge points according to claim 7, It is characterized in that The step of sending the knowledge text contained in the first target knowledge point and the link of the knowledge point having the association relationship with the first target knowledge point comprises: Generate link information based on the viewing order corresponding to the first target knowledge point, wherein the plurality of knowledge points having the association relationship with the first target knowledge point included in the link information are sorted according to the viewing order corresponding to the first target knowledge point; The link information is sent to the client.

9. A device for acquiring association relationships between knowledge points, It is characterized in that include: A first acquisition module is used to acquire a query log, wherein the query log includes query statements respectively input by multiple users and knowledge points corresponding to the query statements; The knowledge point corresponding to the query statement is a knowledge point that satisfies a preset condition in the query result corresponding to the query statement; A second acquisition module is used to obtain multiple query combinations from the query log, where the query combination includes a user identifier and knowledge points corresponding to multiple query statements input by a user having the user identifier; A third acquisition module is used to obtain multiple knowledge points whose co-occurrence frequency is greater than or equal to a first threshold from multiple query combinations, wherein at least two of the multiple knowledge points correspond to different query statements; a construction module is used to construct an association relationship between the multiple knowledge points; The knowledge point includes a knowledge text, a location of the knowledge text in a source document, a first identifier, and a second identifier; the first identifier is an identifier of a knowledge point corresponding to a previous knowledge text in the source document located at the knowledge text; The second identifier is an identifier of a knowledge point corresponding to the next knowledge text located in the source document of the knowledge text; The source document is split into multiple knowledge texts; The method for acquiring the association relationship between knowledge points also includes: For any of the knowledge points, adding a first association identifier of a knowledge point having the association relationship with the knowledge point to the knowledge point; The knowledge text included in the knowledge point having the first association identifier and the knowledge text included in the knowledge point belong to different source documents.

Images