CN115662607B

CN115662607B - Internet online inquiry recommendation method based on big data analysis and server

Info

Publication number: CN115662607B
Application number: CN202211594010.3A
Authority: CN
Inventors: 王觅也; 李楠; 李玲玲; 罗凯
Original assignee: Sichuan University
Current assignee: Sichuan University
Priority date: 2022-12-13
Filing date: 2022-12-13
Publication date: 2023-04-07
Anticipated expiration: 2042-12-13
Also published as: CN115662607A

Abstract

The embodiment of the invention provides an internet online inquiry recommending method and a server based on big data analysis. By the method and the system, the inquirer can check the information of other on-line inquiry logs which are strongly associated with the inquirer and are similar to the inquirer, and the accuracy of the inquirer on disease comparison is improved.

Description

Internet online inquiry recommendation method based on big data analysis and server

Technical Field

The application relates to the field of medical internet, in particular to an internet online inquiry recommendation method and a server based on big data analysis.

Background

With the increasing development of internet technology, the medical industry is changed, and people can not only register for payment through the internet, but also perform on-line inquiry. In addition, when the user is in doubt of physical conditions or uncertain about symptoms, the user often is used to search related symptoms in a search engine, judge according to self conditions, and then evaluate whether to seek medical advice or serve as registration guidance based on the result of preliminary judgment. Therefore, accurate feedback is carried out on disease searching information, potential patients can be helped to accurately recognize self conditions, accurate cut-in of follow-up medical resources is facilitated, and accuracy of disease searching feedback in the prior art needs to be improved.

Disclosure of Invention

The invention aims to provide an internet on-line inquiry recommendation method and a server based on big data analysis, so as to improve the problems.

The embodiment of the application is realized by the following modes:

in a first aspect, an embodiment of the present application provides an internet online inquiry recommendation method based on big data analysis, which is applied to a server, and the method includes:

acquiring N past online inquiry logs of an inquiry object related to the target online inquiry log, wherein N is more than or equal to 1;

respectively determining the similarity degree of the inquiry events of the target on-line inquiry logs and each past on-line inquiry log, and acquiring N temporary on-line inquiry logs of which the similarity degree of the inquiry events meets the requirement of the similarity degree of the inquiry events from the N past on-line inquiry logs;

acquiring a correlated online inquiry log which is in the same online inquiry event type as the target online inquiry log in the N temporary online inquiry logs;

deploying an online inquiry log database corresponding to the online inquiry event type, wherein the online inquiry log database comprises the target online inquiry log and the associated online inquiry log;

acquiring an on-line inquiry log calling instruction;

and responding to the on-line inquiry log calling instruction to call the corresponding on-line inquiry log in the on-line inquiry log database, and sending the associated information of the on-line inquiry log database.

Optionally, if the on-line inquiry logs corresponding to the on-line inquiry log database are classified as on-line inquiry logs having a periodic time sequence association relationship, the obtaining N past on-line inquiry logs of the inquiry objects associated with the target on-line inquiry log includes:

acquiring inquiry description information corresponding to the inquiry logs on the target line;

information mining is carried out on the inquiry description information to obtain target on-line inquiry log representative information of the target on-line inquiry logs;

determining the on-line inquiry log classification of the target on-line inquiry log according to the representative information of the target on-line inquiry log;

if the on-line inquiry logs indicate that the target on-line inquiry logs are on-line inquiry logs with a staged time sequence incidence relation in a classified manner, acquiring N past on-line inquiry logs of inquiry objects related to the target on-line inquiry logs, wherein N is larger than or equal to 1.

Optionally, when the on-line inquiry logs corresponding to the on-line inquiry log database are classified as on-line inquiry logs having a periodic time sequence association relationship, the determining the degree of commonality between the target on-line inquiry log and the inquiry events of each past on-line inquiry log respectively includes:

respectively acquiring inquiry description information corresponding to each online inquiry log, and mining the inquiry description information to obtain target online inquiry log representative information of each online inquiry log;

respectively determining the classification of the on-line inquiry logs of each past on-line inquiry log according to the representative information of the target on-line inquiry logs, and determining that the obtained on-line inquiry logs are classified into the past on-line inquiry logs of the on-line inquiry logs with a stage time sequence correlation relationship;

and respectively determining the inquiry event commonalities of past online inquiry logs of the online inquiry logs classified as the online inquiry logs with the stage time sequence incidence relation between the target online inquiry logs and the online inquiry logs.

Optionally, the determining the similarity degree between the inquiry events of the target online inquiry log and each past online inquiry log respectively includes any one of the following manners:

acquiring first inquiry description information corresponding to the inquiry logs on the target line and second inquiry description information corresponding to each inquiry log on the past line;

performing knowledge extraction on the first inquiry description information to obtain first inquiry description knowledge corresponding to the inquiry logs on the target line;

respectively extracting knowledge of second inquiry description information corresponding to each online inquiry log to obtain second inquiry description knowledge corresponding to each online inquiry log;

respectively determining the quantitative commonality degree of the first inquiry description knowledge and each second inquiry description knowledge, and taking the quantitative commonality degree of the first inquiry description knowledge and each second inquiry description knowledge as the commonality degree of the inquiry events of the target on-line inquiry log and each past on-line inquiry log;

or;

extracting the inquiry session information of the inquiry logs on the target line and the inquiry session information of each inquiry log on the past line;

performing knowledge extraction on the inquiry session information of the target on-line inquiry log to obtain a first inquiry session knowledge element corresponding to the target on-line inquiry log;

respectively extracting knowledge from the inquiry session information of each online inquiry log to obtain a second inquiry session knowledge element corresponding to each online inquiry log;

and respectively determining the quantitative commonality degree of the first inquiry session knowledge element and each second inquiry session knowledge element, and taking the quantitative commonality degree of the first inquiry session knowledge element and each second inquiry session knowledge element as the inquiry event commonality degree of the inquiry logs on the target line and the inquiry logs on the past lines.

Optionally, the obtaining N temporary online inquiry logs, in which the inquiry event commonality degree meets the inquiry event commonality degree requirement, from the N past online inquiry logs includes:

determining the online inquiry logs of which the inquiry event commonality degree is within a preset range in the N online inquiry logs according to the inquiry event commonality degree of the target online inquiry log and each online inquiry log;

and taking the past online inquiry log with the inquiry event commonality degree within a preset range as a temporary online inquiry log with the inquiry event commonality degree meeting the inquiry event commonality degree requirement.

Optionally, the obtaining of the associated online inquiry log in the N temporary online inquiry logs, which is of the same online inquiry event type as the target online inquiry log, includes any one of the following manners:

acquiring first inquiry log annotation information of the target on-line inquiry logs and second inquiry log annotation information of each temporary on-line inquiry log;

matching the first inquiry log annotation information with each second inquiry log annotation information one by one, and determining the matching degree of the first inquiry log annotation information and each second inquiry log annotation information;

if the matching degree meets a preset value, taking the temporary on-line inquiry log corresponding to the annotation information of the second inquiry log as an associated on-line inquiry log which is of the same on-line inquiry event type as the target on-line inquiry log;

or;

performing disassembly operation on the inquiry description information corresponding to the inquiry logs on the target line to obtain a first visual description block set corresponding to the inquiry logs on the target line;

respectively carrying out disassembly operation on the inquiry description information corresponding to each temporary on-line inquiry log to obtain a second visual description block set corresponding to each temporary on-line inquiry log;

respectively determining intersection proportions between the first visual description block set and each second visual description block set;

taking a temporary on-line inquiry log corresponding to the second visual description block set with the intersection proportion meeting a first preset proportion value as an associated on-line inquiry log which is of the same on-line inquiry event type as the target on-line inquiry log;

or;

disassembling the inquiry description information corresponding to the target on-line inquiry log to obtain a first visual description block set corresponding to the target on-line inquiry log;

determining a locking identical visual description block between the first set of visual description blocks and each of the second set of visual description blocks and a proportion of existence of the locking identical visual description block in the second set of visual description blocks, respectively;

and taking the temporary on-line inquiry log corresponding to the locked same visual description block with the proportion meeting a second preset proportion value as an associated on-line inquiry log of the same on-line inquiry event type with the target on-line inquiry log.

Optionally, the deploying an online inquiry log database corresponding to the online inquiry event type includes any one of the following manners:

when the number of the inquiry logs on the associated line is not less than two, respectively acquiring the generation time of the inquiry logs on the target line and the generation time of each inquiry log on the associated line;

arranging the inquiry logs on the target line and the inquiry logs on each associated line according to the time sequence relation of the generation time to obtain a first on-line inquiry log cluster;

deploying an online inquiry log database corresponding to the online inquiry event type through the first online inquiry log cluster;

or;

when the number of the on-line inquiry logs is not less than two, acquiring first inquiry description information corresponding to the on-line inquiry logs of the target line and second inquiry description information corresponding to each on-line inquiry log of the correlation line;

performing diagnosis stage information mining on the first inquiry description information to obtain first diagnosis stage information of the inquiry logs on the target line, and performing diagnosis stage information mining on each second inquiry description information to obtain second diagnosis stage information of the inquiry logs on the corresponding associated line; wherein the diagnostic stage information characterizes a generation order of the corresponding on-line interrogation logs;

arranging the on-target line inquiry logs and the plurality of associated on-line inquiry logs according to the first diagnosis stage information and the second diagnosis stage information in a time sequence to obtain a second on-line inquiry log cluster;

deploying an online inquiry log database corresponding to the online inquiry event type through the second online inquiry log cluster;

or;

determining a difference value of two random generation moments, and when the difference value meets a preset difference value, respectively performing diagnosis stage information mining on the inquiry logs on the target line and the inquiry logs on each associated line to obtain corresponding diagnosis stage information, wherein the diagnosis stage information represents a generation sequence of the corresponding inquiry logs on the line;

arranging the inquiry logs on the target line and each inquiry log on the associated line according to the diagnosis stage information in a time sequence to obtain an inquiry log cluster on a third line;

and deploying an online inquiry log database corresponding to the online inquiry event type through the third online inquiry log cluster.

Optionally, the sending the associated information of the online inquiry log database includes:

and sending the associated information of the on-line inquiry log database to query equipment, wherein the associated information comprises the link information of the on-line inquiry log database and the annotation information of the on-line inquiry log database.

In a second aspect, an embodiment of the present application provides a server, including a processor and a memory, which are in communication with each other, where the memory stores a program, and the processor is configured to retrieve a computer program from the memory and implement the method provided in the first aspect of the embodiment of the present application by executing the computer program.

The online inquiry recommending method based on big data analysis, provided by the embodiment of the invention, comprises the steps of firstly obtaining N past online inquiry logs of an inquiry object associated with the target online inquiry logs, then obtaining N temporary online inquiry logs with inquiry event consistency meeting requirements according to the inquiry event commonality degree of the target online inquiry logs and each past online inquiry log, then obtaining associated online inquiry logs with the same type as the target online inquiry logs in the N temporary online inquiry logs, deploying an online inquiry log database corresponding to the online inquiry event type, and when obtaining an online inquiry log retrieving instruction, retrieving the online inquiry logs in the corresponding online inquiry log database in response to the online inquiry log retrieving instruction, and sending associated information of the online inquiry log database. Because the on-line inquiry logs included in the on-line inquiry log database are the same inquiry objects, the inquiry event common degree meets the requirements and the on-line inquiry logs are of the same type, the on-line inquiry logs in the on-line inquiry log database have higher correlation, when the on-line inquiry logs in the on-line inquiry log database are acquired, the correlation information of the on-line inquiry log database is sent, and an inquirer can check the information of other on-line inquiry logs which are strongly correlated with the on-line inquiry logs and belong to the same type according to the correlation information, so that the accuracy of the inquirer on disease comparison is improved.

In the following description, other features will be set forth in part. These features will be in part apparent to those skilled in the art upon examination of the following and the accompanying drawings, or may be learned by production or use. The features of the present application may be realized and attained by practice or use of various aspects of the methodologies, instrumentalities and combinations particularly pointed out in the detailed examples that follow.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

The methods, systems, and/or processes of the figures are further described in accordance with the exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments in which reference numerals represent similar mechanisms throughout the various views of the drawings.

Fig. 1 is a block diagram of an interrogation system, shown in accordance with some embodiments of the present application.

FIG. 2 is a schematic diagram illustrating the hardware and software components in a server according to some embodiments of the present application.

FIG. 3 is a flow diagram of a method for online inquiry recommendation based on big data analysis, according to some embodiments of the present application.

Fig. 4 is a schematic structural diagram of an online inquiry recommendation device according to an embodiment of the present application.

Detailed Description

In order to better understand the technical solutions, the technical solutions of the present application are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.

In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant guidance. It will be apparent, however, to one skilled in the art that the present application may be practiced without these specific details. In other instances, well-known methods, procedures, systems, components, and/or circuits have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.

These and other features, functions, methods of execution, and combination of functions and elements of related elements in the structure and economies of manufacture disclosed in the present application may become more apparent upon consideration of the following description with reference to the accompanying drawings, all of which form a part of this application. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the application. It should be understood that the drawings are not to scale. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the application. It should be understood that the drawings are not to scale.

Flowcharts are used herein to illustrate the implementations performed by systems according to embodiments of the present application. It should be expressly understood that the processes performed by the flowcharts may be performed out of order. Rather, these implementations may be performed in the reverse order or simultaneously. In addition, N other implementations may be added to the flowchart. One or more implementations may be deleted from the flowchart.

Fig. 1 is a block diagram of a system architecture of an interrogation system 300, shown according to some embodiments of the present application, which interrogation system 300 may include a server 100 and a plurality of query terminals 200 in communication therewith.

The query terminal 200 is a device used when the target user receives the service data, and may be, for example, a personal computer, a notebook computer, a tablet computer, a smart phone, or the like having a network interaction function.

In some embodiments, please refer to fig. 2, which is a schematic diagram of an architecture of a server 100, where the server 100 includes an online inquiry recommending device 110, a memory 120, a processor 130, and a communication unit. The memory 120, the processor 130, and the communication unit are electrically connected to each other directly or indirectly to enable data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The on-line inquiry recommending device 110 includes N software functional modules which can be stored in the memory 120 in the form of software or firmware (firmware) or solidified in an Operating System (OS) of the server 100. The processor 130 is used to execute executable modules stored in the memory 120, such as software functional modules and computer programs included in the teleeducation-based business information processing apparatus 110.

The Memory 120 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 120 is used for storing a program, and the processor 130 executes the program after receiving the execution instruction. The communication unit is used for establishing a communication connection between the server 100 and the inquiry terminal through a network, and for transceiving data through the network.

The processor may be an integrated circuit chip having signal processing capabilities. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP)), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It will be appreciated that the configuration shown in fig. 2 is merely illustrative and that server 100 may include more or fewer components than shown in fig. 2 or have a different configuration than shown in fig. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.

Fig. 3 is a flowchart of an internet online inquiry recommendation method based on big data analysis according to some embodiments of the present application, and the method is applied to the server 100 in fig. 1, and may specifically include the following steps S1 to S6. On the basis of the following steps S1 to S6, some alternative embodiments will be described, which should be understood as examples and should not be understood as technical features essential for implementing the present solution.

S1, N past online inquiry logs of an inquiry object associated with the target online inquiry log are obtained, wherein N is larger than or equal to 1.

In this embodiment, the obtained execution subject is the server 100, and the online inquiry log may be interactive information formed when the patient (or the consultant) interacts with the inquiry subject (the doctor or the physician) on the internet to generate an interactive behavior for the disease condition, and form data such as a report, a web page, a compressed package, and the like, which may include content such as session information, a diagnosis result, and medical order information. The past on-line inquiry log is the on-line inquiry log which is completed by the inquiry subjects and is completed in stages. In this embodiment, the accuracy of recommending the on-line inquiry logs can be improved by deploying the on-line inquiry log aggregation database for the target on-line inquiry logs, and when the on-line inquiry log aggregation database for the target on-line inquiry logs is deployed, a plurality of past on-line inquiry logs of inquiry objects associated with the target on-line inquiry logs can be obtained first. The query subject is the responder included in the target on-line query log.

As an embodiment, when the on-line inquiry logs corresponding to the on-line inquiry log aggregation database are classified as on-line inquiry logs having a staged time-series association relationship, N past on-line inquiry logs of an inquiry object associated with the target on-line inquiry log may be obtained based on the following steps: acquiring inquiry description information corresponding to an inquiry log on a target line; information mining is carried out on the inquiry description information to obtain representative information of the on-target-line inquiry logs; determining the on-line inquiry log classification of the on-line inquiry log of the target line according to the representative information of the on-line inquiry log of the target line; and if the on-line inquiry log classification indicates that the target on-line inquiry log is an on-line inquiry log with a stage time sequence association relationship, acquiring N past on-line inquiry logs of inquiry objects associated with the target on-line inquiry log, wherein N is more than or equal to 1.

For this embodiment, if the on-line inquiry logs corresponding to the deployed on-line inquiry log aggregation database are classified as on-line inquiry logs having a staged time sequence association relationship, that is, when the on-line inquiry logs of the target on-line inquiry log in the on-line inquiry log aggregation database are classified as on-line inquiry logs having a staged time sequence association relationship, when obtaining the past on-line inquiry logs of the inquiry objects associated with the target on-line inquiry logs, it is necessary to determine the on-line inquiry log classification of the on-line inquiry logs first. In the present application, having a staged time-series correlation means that a plurality of on-line inquiry logs are sequential and have correlation at the same time, for example, in an on-line inquiry of the same disease condition, a set of on-line inquiry logs of a patient, such as initial inquiry, pathological examination, report analysis, re-diagnosis, confirmed diagnosis, etc., are collected. Optionally, the online inquiry log classifications of the target online inquiry logs may be differentiated based on: acquiring inquiry description information corresponding to the inquiry logs on the target line, such as inquiry description information such as log head-up information and summary information; then, information mining is carried out on the inquiry description information corresponding to the on-target-line inquiry logs to obtain on-target-line inquiry log representative information of the on-target-line inquiry logs, wherein the representative information can be used for indicating the types of the logs, for example, the representative information comprises the information of the follow-up and the same patient; and determining the on-line inquiry log classification of the target on-line inquiry log according to the representative information of the target on-line inquiry log. For example, when the inquiry description information of the excavated on-target-line inquiry log includes on-target-line inquiry log representative information such as "initial diagnosis", "follow-up diagnosis", "report interpretation" and "follow-up examination", it can be confirmed that the on-target-line inquiry log of the on-target-line inquiry log is classified as an on-target-line inquiry log having a stepwise time-series correlation.

After the classification of the on-line inquiry logs of the target on-line inquiry logs is determined, if the classification of the on-line inquiry logs indicates that the on-line inquiry logs of the target are on-line inquiry logs with a stage time sequence association relationship, the on-line inquiry logs of the inquiry objects associated with the on-line inquiry logs of the target can be obtained, so as to deploy an on-line inquiry log aggregation database of the on-line inquiry logs with the stage time sequence association relationship according to the on-line inquiry logs of the target. If the on-line inquiry log classification indicates that the target on-line inquiry log is not the on-line inquiry log with the staged time sequence incidence relation, the on-line inquiry log collection database of the on-line inquiry log with the staged time sequence incidence relation cannot be deployed according to the target on-line inquiry log.

And S2, respectively determining the similarity degree of the inquiry events of the target on-line inquiry logs and the past on-line inquiry logs, and acquiring N temporary on-line inquiry logs with the inquiry event similarity degree meeting the inquiry event similarity degree requirement from the N past on-line inquiry logs. In the embodiment of the application, after a plurality of past online inquiry logs of an inquiry object associated with a target online inquiry log are obtained, the inquiry event commonality degree of the target online inquiry log and each past online inquiry log can be respectively determined, so that a temporary online inquiry log with the inquiry event commonality degree requirement met by the inquiry event commonality degree is obtained from the plurality of past online inquiry logs. For this embodiment, the inquiry event commonality degree represents the proximity or similarity between the two, the inquiry event commonality requirement may be a preset inquiry event commonality degree range, and the online inquiry log with the inquiry event commonality degree within the inquiry event commonality range is used as the temporary online inquiry log. For example, the inquiry event commonality degree range is from a first inquiry event commonality degree to a second inquiry event commonality degree, it is easy to understand that the first inquiry event commonality degree is less than the second inquiry event commonality degree, on this basis, a past online inquiry log with an inquiry event commonality degree greater than the first inquiry event commonality degree and less than the second inquiry event commonality degree can be used as a temporary online inquiry log, wherein, numerical values of the first inquiry event commonality degree and the second inquiry event commonality degree can be set practically, and the present application is not limited thereto. In the embodiment of the present application, the degree of commonness between the inquiry events of the target online inquiry log and each past online inquiry log may be determined based on the following steps: acquiring first inquiry description information corresponding to the inquiry logs on the target line and second inquiry description information corresponding to the inquiry logs on each past line; performing knowledge extraction on the first inquiry description information to obtain first inquiry description knowledge corresponding to the inquiry logs on the target line; respectively extracting knowledge of second inquiry description information corresponding to each online inquiry log to obtain second inquiry description knowledge corresponding to each online inquiry log; and respectively determining the quantitative commonality degree of the first inquiry description knowledge and each second inquiry description knowledge, and taking the quantitative commonality degree of the first inquiry description knowledge and each second inquiry description knowledge as the commonality degree of the inquiry events of the target on-line inquiry log and each past on-line inquiry log. In this embodiment, when determining the degree of commonalities between the target online inquiry log and the inquiry events of the respective past online inquiry logs, the user can determine the degree of commonalities by using the target online inquiry log and the corresponding inquiry description information of each past online inquiry log. In detail, first inquiry description information related to the target on-line inquiry logs and second inquiry description information corresponding to each past on-line inquiry log are obtained; then, performing knowledge extraction (or feature extraction) on the first inquiry description information to obtain first inquiry description knowledge corresponding to the inquiry logs on the target line, and performing knowledge extraction on each second inquiry description information to obtain second inquiry description knowledge corresponding to each past inquiry log on the target line, wherein the knowledge extraction process can be realized by adopting a pre-trained knowledge extraction model, such as the existing mature entity extraction, relationship extraction or event extraction technology; after obtaining the first inquiry description knowledge corresponding to the inquiry log on the target line and the second inquiry description knowledge corresponding to the inquiry log on each past line, determining a quantitative commonality degree of the first inquiry description knowledge and each second inquiry description knowledge (for example, a value obtained by calculating a distance between the first inquiry description knowledge and each second inquiry description knowledge after knowledge vectorization), for example, calculating a cosine distance or an euclidean distance to obtain a commonality degree of the inquiry events, and using the quantitative commonality degree of the first inquiry description knowledge and each second inquiry description knowledge as the commonality degree of the inquiry events between the inquiry log on the target line and each past line.

As some embodiments, the degree of commonalities of the interrogation events between the target online interrogation log and each past online interrogation log may also be determined separately based on the following steps: extracting the inquiry session information of the inquiry logs on the target line and the inquiry session information of each inquiry log on the past line; performing knowledge extraction on the inquiry session information of the inquiry logs on the target line to obtain a first inquiry session knowledge element corresponding to the inquiry logs on the target line; respectively extracting knowledge of the inquiry session information of each online inquiry log to obtain a second inquiry session knowledge element corresponding to each online inquiry log; and respectively determining the quantitative commonality degree of the first inquiry session knowledge element and each second inquiry session knowledge element, and taking the quantitative commonality degree of the first inquiry session knowledge element and each second inquiry session knowledge element as the inquiry event commonality degree of the target online inquiry log and each past online inquiry log.

In this embodiment, when determining the degree of commonality between the on-target-line inquiry log and the inquiry events of the on-past-line inquiry logs, the degree of commonality may be determined by the on-target-line inquiry log and the inquiry session information included in each on-past-line inquiry log, and the inquiry session information may be information generated by session behaviors such as information exchange between a patient and a physician, patient payment, and patient review. In detail, by extracting the inquiry session information of the target online inquiry log and the inquiry session information of each past online inquiry log, the inquiry session information is easy to understand, and the number of the inquiry session information can be multiple; then, performing knowledge extraction on the inquiry session information of the inquiry logs on the target line, namely performing knowledge extraction on each inquiry session information to obtain a knowledge element (or characteristic) of each inquiry session information, and fusing the knowledge elements of each inquiry session information to obtain a first inquiry session knowledge element corresponding to the inquiry logs on the target line; in addition, knowledge extraction is carried out on the inquiry session information of each on-line inquiry log, in other words, knowledge extraction is carried out on each inquiry session information contained in each on-line inquiry log to obtain knowledge elements of each inquiry session information, and the knowledge elements of each target on-line inquiry log are fused to obtain a second inquiry session knowledge element corresponding to each on-line inquiry log; after a first inquiry session knowledge element corresponding to the inquiry logs on the target line and a second inquiry session knowledge element corresponding to the inquiry logs on each past line are obtained, the quantitative commonality degree, such as cosine distance, between the first inquiry session knowledge element and each second inquiry session knowledge element is calculated, and the quantitative commonality degree between the first inquiry session knowledge element and each second inquiry session knowledge element is used as the inquiry event commonality degree of the inquiry logs on the target line and each past line. As some embodiments, when the on-line inquiry logs corresponding to the on-line inquiry log collection database are classified as on-line inquiry logs having a staged time-series association relationship, the following steps may be adopted to respectively determine the degree of commonality between the target on-line inquiry log and each past on-line inquiry log: respectively obtaining inquiry description information corresponding to each on-line inquiry log, and mining the information of each inquiry description information to obtain the representative information of the on-line inquiry log of each on-line inquiry log; determining the classification of the on-line inquiry logs of each past on-line inquiry log one by one according to the representative information of the target on-line inquiry logs, and determining that the obtained on-line inquiry logs are classified into the past on-line inquiry logs of the on-line inquiry logs with the stage time sequence correlation relationship; and respectively determining the inquiry event commonalities of the past online inquiry logs of the online inquiry logs with the stage time sequence incidence relation classified by the target online inquiry logs and the online inquiry logs. In this embodiment, when the on-line inquiry logs corresponding to the deployed on-line inquiry log corpus database are classified as on-line inquiry logs having a staged time-sequence correlation, in other words, when the on-line inquiry logs of the target on-line inquiry log in the on-line inquiry log corpus database are classified as on-line inquiry logs having a staged time-sequence correlation, in order to save the calculation overhead when determining the inquiry event commonality between the target on-line inquiry log and each of the past on-line inquiry logs, the on-line inquiry logs having a staged time-sequence correlation may be selected first, and then the inquiry event commonality between the target on-line inquiry log and the selected on-line inquiry log classified as the past on-line inquiry log of the on-line inquiry log having a staged time-sequence correlation may be determined. In detail, the determination of the on-line inquiry log classification of the target on-line inquiry log may be made based on the following steps: acquiring inquiry description information corresponding to an inquiry log on a target line; then, information mining is carried out on the inquiry description information corresponding to the inquiry logs on the target line, and representative information of the inquiry logs on the target line is obtained; then, the on-line inquiry log classification of the target on-line inquiry log is determined according to the representative information of the target on-line inquiry log, for example, as described above, which is not described herein again.

As an embodiment, the following steps may be adopted to obtain N temporary online inquiry logs with the inquiry event commonality meeting the inquiry event commonality requirement: determining the online inquiry logs of the N past online inquiry logs according to the inquiry event commonality degree of the target online inquiry log and each past online inquiry log, wherein the inquiry event commonality degree of the online inquiry logs of the N past online inquiry logs is within a preset range; and taking the past online inquiry logs with the inquiry event commonality degree within the preset range as temporary online inquiry logs with the inquiry event commonality degree meeting the inquiry event commonality degree requirement.

And S3, acquiring the associated online inquiry logs, which are of the same online inquiry time type as the target online inquiry logs, in the N temporary online inquiry logs. After the obtained N past online inquiry logs are selected according to the inquiry event commonality, the obtained N temporary online inquiry logs can be further filtered, namely, the associated online inquiry logs of the N temporary online inquiry logs, which are in the same online inquiry time type with the target online inquiry log, are obtained. As some embodiments, the associated online inquiry logs of the N temporary online inquiry logs of the same online inquiry time type as the target online inquiry log may be obtained based on the following steps: acquiring first inquiry log annotation information of an inquiry log on a target line and second inquiry log annotation information of each temporary inquiry log on the target line; matching the first inquiry log annotation information with each second inquiry log annotation information one by one to obtain the matching degree of the first inquiry log annotation information and each second inquiry log annotation information; and if the matching degree meets the preset value, taking the temporary on-line inquiry log corresponding to the annotation information of the second inquiry log as an associated on-line inquiry log which has the same on-line inquiry time type as the target on-line inquiry log.

When the information of the on-line inquiry log is displayed in a public way, annotation information such as disease types, disease grades, patient conditions (sex, age or age range) and the like can be attached, and the server can extract the annotation information of the inquiry log based on the content of the on-line inquiry log in the process of processing the on-line inquiry log. In this embodiment, when acquiring an associated online inquiry log of the N temporary online inquiry logs, which is of the same online inquiry time type as the target online inquiry log, first acquiring first inquiry log annotation information of the target online inquiry log and second inquiry log annotation information of each temporary online inquiry log, and then matching the first inquiry log annotation information with each second inquiry log annotation information one by one to obtain a matching degree between the first inquiry log annotation information and each second inquiry log annotation information, so that the temporary online inquiry log corresponding to the second inquiry log annotation information of which the matching degree satisfies a preset value is used as the associated online inquiry log of the same online inquiry time type as the target online inquiry log.

On the basis of the above embodiment, as a feasible embodiment, the following steps may be adopted to obtain the associated online inquiry logs in the N temporary online inquiry logs, which are of the same online inquiry time type as the target online inquiry log: performing disassembly operation on inquiry description information corresponding to the inquiry logs on the target line to obtain a first visual description block set corresponding to the inquiry logs on the target line; respectively carrying out disassembly operation on the inquiry description information corresponding to each temporary on-line inquiry log to obtain a second visual description block set corresponding to each temporary on-line inquiry log; respectively determining intersection proportions between the first visual description block set and each second visual description block set; and taking the temporary on-line inquiry log corresponding to the second visual description block set with the intersection proportion meeting the first preset proportion value as an associated on-line inquiry log which is of the same on-line inquiry time type with the target on-line inquiry log.

In this embodiment, the on-line inquiry log may be obtained by analyzing the inquiry description information of the temporary on-line inquiry log and the target on-line inquiry log, wherein the on-line inquiry description information is associated with the on-line inquiry time type of the temporary on-line inquiry logs. In detail, the method may first perform a disassembling operation on the inquiry description information corresponding to the inquiry log on the target line to obtain a first visual description block set corresponding to the inquiry log on the target line, where the first visual description block set is a set of each block obtained by splitting the inquiry description information; then, disassembling the inquiry description information corresponding to each temporary on-line inquiry log to obtain a second visual description block set corresponding to each temporary on-line inquiry log; determining intersection proportion between the first visual description block set and each second visual description block set one by one, namely coincidence degree between the two sets; and finally, determining a temporary on-line inquiry log corresponding to the second visual description block set with the intersection proportion reaching the first preset proportion value from the plurality of temporary on-line inquiry logs as an associated on-line inquiry log which is of the same on-line inquiry time type as the target on-line inquiry log. As an embodiment, the following steps may be taken to obtain the associated online inquiry log of the N temporary online inquiry logs, which is of the same online inquiry time type as the target online inquiry log: disassembling inquiry description information corresponding to the inquiry logs on the target line to obtain a first visual description block set corresponding to the inquiry logs on the target line; respectively carrying out disassembly operation on the inquiry description information corresponding to each temporary on-line inquiry log to obtain a second visual description block set corresponding to each temporary on-line inquiry log; determining existence proportions of the locked identical visual description blocks and the locked identical visual description blocks in the second visual description block sets respectively between the first visual description block set and each second visual description block set; and taking the temporary on-line inquiry logs corresponding to the locked same visual description blocks with the existing proportion meeting a second preset proportion value as associated on-line inquiry logs with the same on-line inquiry time type as the target on-line inquiry logs.

In this embodiment, the associated online inquiry logs in the plurality of temporary online inquiry logs and the target online inquiry log may be obtained in the same online inquiry time type as the target online inquiry log based on analyzing the inquiry description information of the temporary online inquiry logs and the target online inquiry logs. In detail, the method may first perform a disassembling operation on the inquiry description information corresponding to the inquiry log on the target line to obtain a first visual description block set corresponding to the inquiry log on the target line, where the first visual description block set includes a plurality of blocks; then, disassembling the inquiry description information corresponding to each temporary on-line inquiry log to obtain a second visual description block set corresponding to each temporary on-line inquiry log; determining locking identical visual description blocks between the first visual description block set and each second visual description block set one by one, namely determining the visual description blocks which exist in the two visual description block sets at the same time, and the existence proportion of each locking identical visual description block in the second visual description block sets; and finally, selecting the temporary on-line inquiry logs corresponding to the locked same visual description blocks with the existence proportion meeting a second preset proportion value from the plurality of temporary on-line inquiry logs, and taking the temporary on-line inquiry logs as associated on-line inquiry logs which are in the same on-line inquiry time type with the target on-line inquiry logs.

And S4, deploying an on-line inquiry log collection database corresponding to the type of the target on-line inquiry time.

Wherein the on-line inquiry log collection database comprises a target on-line inquiry log and an associated on-line inquiry log. In an embodiment of the present application, the following steps may be employed to deploy an online interrogation log collection database corresponding to a type of target online interrogation time: if the number of the inquiry logs on the associated lines is not less than two, respectively obtaining the generation time of the inquiry logs on the target line and the inquiry logs on each associated line; arranging the inquiry logs on the target line and the inquiry logs on each associated line according to the time sequence relation of the generation time to obtain a first on-line inquiry log cluster; and deploying an online inquiry log collection database corresponding to the type of the target online inquiry time through the first online inquiry log cluster, for example, selecting a certain number of associated online inquiry logs with close generation time to deploy an online inquiry log collection database containing the target online inquiry logs and the associated online inquiry logs.

In this embodiment, when the on-line inquiry log collection database corresponding to the type of the on-target line inquiry time is deployed through the on-target line inquiry log and the associated on-line inquiry log, the on-target line inquiry log and the associated on-line inquiry log can be arranged in time sequence, for example, the on-line inquiry log collection database having a periodic time sequence association relationship, and the on-target line inquiry logs in the on-line inquiry log collection database can be arranged in time sequence, for example, "first diagnosis", "first inspection", "second diagnosis", and the like, which is beneficial for an inquirer to view in sequence. In addition, when the on-target line inquiry logs and the associated on-line inquiry logs are arranged in time sequence, the generation time of the on-target line inquiry logs and the generation time of each associated on-line inquiry log can be respectively obtained, then based on the time sequence of the generation time, the on-target line inquiry logs and each associated on-line inquiry logs are arranged in time sequence to obtain a first on-line inquiry log cluster, and therefore the on-line inquiry log aggregation database is arranged according to the first on-line inquiry log cluster. In another embodiment, an online interrogation log collection database corresponding to a type of target online interrogation time may be deployed according to the following steps: when the number of the inquiry logs on the associated lines is not less than two, acquiring first inquiry description information corresponding to the inquiry logs on the target line and second inquiry description information corresponding to the inquiry logs on each associated line; performing diagnosis stage information mining on the first inquiry description information to obtain first diagnosis stage information of an inquiry log on a target line, and performing diagnosis stage information mining on each second inquiry description information to obtain second diagnosis stage information of the inquiry log on a corresponding correlation line; arranging the inquiry logs on the target line and the plurality of inquiry logs on the associated line according to the first diagnosis stage information and the second diagnosis stage information to obtain a second inquiry log cluster on the line; and deploying an online inquiry log collection database corresponding to the type of the online inquiry time of the target through a second online inquiry log cluster. In the embodiment of the application, the diagnosis stage information is used for representing the generation sequence of the inquiry logs on the corresponding target line.

In this embodiment, the inquiry description information of the target online inquiry log and the associated online inquiry log may be arranged in time sequence. In detail, first inquiry description information corresponding to the inquiry logs on the target line and second inquiry description information corresponding to the inquiry logs on each associated line are obtained, then diagnosis stage information mining is carried out on the first inquiry description information to obtain first diagnosis stage information of the inquiry logs on the target line, and diagnosis stage information mining is carried out on each second inquiry description information to obtain second diagnosis stage information of the inquiry logs on the associated lines, such as 'follow-up diagnosis', 'review', 'prescription notes' and the like; then, according to the first diagnosis stage information and the second diagnosis stage information, arranging the on-target-line inquiry logs and the plurality of associated on-line inquiry logs in a time sequence to obtain a second on-line inquiry log cluster as an implementation mode, and deploying an on-line inquiry log collection database corresponding to the on-target-line inquiry time type by adopting the following steps: if the number of the inquiry logs on the associated lines is not less than two, respectively obtaining the generation time of the inquiry logs on the target line and the inquiry logs on each associated line; determining the difference value of two random generation moments; when the difference value meets a preset difference value, diagnosis stage information mining is respectively carried out on the inquiry logs on the target line and the inquiry logs on each associated line, and corresponding diagnosis stage information is obtained; arranging the inquiry logs on the target line and the inquiry logs on each associated line according to the diagnosis stage information to obtain an inquiry log cluster on a third line; and deploying an online inquiry log collection database corresponding to the type of the target online inquiry time through a third online inquiry log cluster. The diagnosis stage information is used for representing the generation sequence of the inquiry logs on the corresponding target line.

In some cases, when the platform side publishes the on-line inquiry logs, sequential publishing may not be performed according to the logic sequence of the on-line inquiry logs, for example, a review report of the on-line inquiry logs is published before a review report, which may cause the arrangement according to the generation time to be disordered. Therefore, the online inquiry log generation time and the inquiry description information can be combined for arrangement. In detail, respectively obtaining the generation time of the inquiry logs on the target line and the inquiry logs on each associated line, and determining the difference between two random generation times; when the difference value meets a preset difference value, respectively carrying out diagnosis stage information mining on the inquiry logs on the target line and the inquiry logs on each associated line to obtain corresponding diagnosis stage information; arranging the inquiry logs on the target line and the inquiry logs on each associated line according to the diagnosis stage information to obtain an inquiry log cluster on a third line; and then deploying an online inquiry log collection database corresponding to the type of the target online inquiry time through a third online inquiry log cluster. As another case, if the difference of the preset difference is not satisfied, the on-line inquiry logs on the target line and the associated on-line inquiry logs are arranged according to the time sequence according to the generation time to obtain a fourth on-line inquiry log cluster, and an on-line inquiry log aggregation database corresponding to the type of the on-line inquiry time is deployed.

And S5, acquiring an on-line inquiry log calling instruction.

In the embodiment of the application, a plurality of deployed online inquiry log databases exist, and when an inquirer searches for symptoms, the inquirer identifies the searched key content and then generates a corresponding online inquiry log calling instruction for positioning the online inquiry log database and the online inquiry logs in the online inquiry log database.

And S6, responding to the on-line inquiry log calling instruction, calling the corresponding on-line inquiry log in the on-line inquiry log database, and sending the associated information of the on-line inquiry log database.

As an embodiment, the association information of the online inquiry log collection database can be sent by the following steps: and sending the associated information of the on-line inquiry log database to query equipment, wherein the associated information comprises the link information of the on-line inquiry log database and the annotation information of the on-line inquiry log database.

In this embodiment, when an inquirer inquires about a related disease, search information can be generated according to a terminal device, a server identifies key content according to the search information, generates an on-line inquiry log calling instruction, calls a corresponding on-line inquiry log from a matched on-line inquiry log database, and sends the on-line inquiry log to the terminal device for display, and simultaneously sends link information of the on-line inquiry log database and annotation information of the on-line inquiry log database, wherein the link information is used as an inlet of the on-line inquiry log database, so that the inquirer can conveniently check other on-line inquiry logs, and the annotation information is used for representing general information of the on-line inquiry log database, and the inquirer can conveniently judge whether the link information needs to be opened.

Referring to fig. 4, which is a schematic structural diagram of an on-line inquiry recommendation apparatus 110 according to an embodiment of the present invention, the on-line inquiry recommendation apparatus 110 may be used to execute an on-line inquiry recommendation method based on big data analysis, where the on-line inquiry recommendation apparatus 110 includes:

the obtaining module 111 is configured to obtain N online inquiry logs of an inquiry object associated with the target online inquiry log, where N is greater than or equal to 1.

The temporary determination module 112 is configured to determine the similarity degree of the inquiry events between the target online inquiry log and each past online inquiry log, and obtain N temporary online inquiry logs, in which the similarity degree of the inquiry events meets the requirement of the similarity degree of the inquiry events, from the N past online inquiry logs.

And the association determining module 113 is configured to obtain an associated online inquiry log, which is of the same online inquiry event type as the target online inquiry log, from the N temporary online inquiry logs.

A deployment module 114, configured to deploy an online inquiry log database corresponding to the type of online inquiry event, where the online inquiry log database includes a target online inquiry log and an associated online inquiry log.

And the instruction acquisition module 115 is used for acquiring an online inquiry log calling instruction.

And the sending module 116 is configured to call the corresponding online inquiry log in the online inquiry log database in response to the online inquiry log calling instruction, and send the associated information of the online inquiry log database.

The obtaining module 111 may be configured to perform step S1; the temporary determination module 112 may be configured to perform step S2; the association determining module 113 may be configured to perform step S3; the deployment module 114 is operable to perform step S4; the instruction obtaining module 115 may be configured to perform step S5; the sending module 116 may be configured to perform step S6.

In the above embodiment, the online inquiry recommendation method based on big data analysis according to the embodiment of the present invention has been described in detail, and the principle of the online inquiry recommendation device 110 is the same as that of the online inquiry recommendation method, so the execution principle of each module of the online inquiry recommendation device 110 is not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative and, for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.

It should be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.

It should be understood that technical terms not nounced in the above-mentioned contents can be clearly determined by those skilled in the art from the above-mentioned disclosures. The above disclosure of the embodiments of the present application will be apparent to those skilled in the art from the above disclosure. It should be understood that the process of deriving and analyzing technical terms, which are not explained, by those skilled in the art based on the above disclosure is based on the contents described in the present application, and thus the above contents are not an inventive judgment of the overall scheme.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.

It should also be appreciated that in the foregoing description of embodiments of the present application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of N inventive embodiments. However, this method of disclosure is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Claims

1. An internet on-line inquiry recommendation method based on big data analysis is applied to a server, and the method comprises the following steps:

acquiring an on-line inquiry log calling instruction;

responding to the on-line inquiry log calling instruction to call the corresponding on-line inquiry log in the on-line inquiry log database, and sending the associated information of the on-line inquiry log database;

when the on-line inquiry logs corresponding to the on-line inquiry log database are classified into on-line inquiry logs with a periodic time sequence incidence relation, the determining the similarity degree of the inquiry events between the target on-line inquiry log and each past on-line inquiry log respectively comprises: respectively obtaining the corresponding inquiry description information of each online inquiry log, and mining the information of each inquiry description information to obtain the representative information of the target online inquiry log of each online inquiry log; respectively determining the classification of the on-line inquiry logs of each past on-line inquiry log according to the representative information of the target on-line inquiry logs, and determining that the obtained on-line inquiry logs are classified into the past on-line inquiry logs of the on-line inquiry logs with a stage time sequence correlation relationship; respectively determining the inquiry event commonness degree of the past online inquiry logs of the target online inquiry logs and the online inquiry logs classified as the online inquiry logs with the stage time sequence incidence relation;

the determining the similarity degree of the inquiry events of the target online inquiry log and each past online inquiry log respectively comprises any one of the following modes: acquiring first inquiry description information corresponding to the target on-line inquiry logs and second inquiry description information corresponding to each past on-line inquiry log; performing knowledge extraction on the first inquiry description information to obtain first inquiry description knowledge corresponding to the inquiry log on the target line; respectively extracting knowledge of second inquiry description information corresponding to each online inquiry log to obtain second inquiry description knowledge corresponding to each online inquiry log; respectively determining the quantitative commonality degree of the first inquiry description knowledge and each second inquiry description knowledge, and taking the quantitative commonality degree of the first inquiry description knowledge and each second inquiry description knowledge as the commonality degree of the inquiry events of the target on-line inquiry log and each past on-line inquiry log; or; extracting the inquiry session information of the target on-line inquiry logs and the inquiry session information of each past on-line inquiry log; performing knowledge extraction on the inquiry session information of the target on-line inquiry log to obtain a first inquiry session knowledge element corresponding to the target on-line inquiry log; respectively carrying out knowledge extraction on the inquiry session information of each online inquiry log to obtain a second inquiry session knowledge element corresponding to each online inquiry log; respectively determining the quantitative commonality degree of the first inquiry session knowledge element and each second inquiry session knowledge element, and taking the quantitative commonality degree of the first inquiry session knowledge element and each second inquiry session knowledge element as the inquiry event commonality degree of the inquiry logs on the target line and the inquiry logs on the past lines;

the obtaining of the associated online inquiry log in the N temporary online inquiry logs, which is of the same online inquiry event type as the target online inquiry log, includes any one of the following manners: acquiring first inquiry log annotation information of the target on-line inquiry logs and second inquiry log annotation information of each temporary on-line inquiry log; matching the first inquiry log annotation information with each second inquiry log annotation information one by one, and determining the matching degree of the first inquiry log annotation information and each second inquiry log annotation information; if the matching degree meets a preset value, taking the temporary on-line inquiry log corresponding to the annotation information of the second inquiry log as an associated on-line inquiry log which is of the same on-line inquiry event type as the target on-line inquiry log; or; disassembling the inquiry description information corresponding to the target on-line inquiry log to obtain a first visual description block set corresponding to the target on-line inquiry log; respectively carrying out disassembly operation on the inquiry description information corresponding to each temporary on-line inquiry log to obtain a second visual description block set corresponding to each temporary on-line inquiry log; respectively determining intersection proportions between the first visual description block set and each second visual description block set; taking a temporary on-line inquiry log corresponding to the second visual description block set with the intersection proportion meeting a first preset proportion value as an associated on-line inquiry log which is of the same on-line inquiry event type as the target on-line inquiry log; or; disassembling the inquiry description information corresponding to the target on-line inquiry log to obtain a first visual description block set corresponding to the target on-line inquiry log; respectively carrying out disassembly operation on the inquiry description information corresponding to each temporary on-line inquiry log to obtain a second visual description block set corresponding to each temporary on-line inquiry log; determining a locking identical visual description block between the first set of visual description blocks and each of the second set of visual description blocks and a proportion of existence of the locking identical visual description block in the second set of visual description blocks, respectively; taking the temporary on-line inquiry logs corresponding to the locked same visual description blocks with the existing proportion meeting a second preset proportion value as associated on-line inquiry logs of the same on-line inquiry event type with the target on-line inquiry logs;

the deploying of the online inquiry log database corresponding to the online inquiry event type comprises any one of the following modes: when the number of the inquiry logs on the associated line is not less than two, respectively acquiring the generation time of the inquiry logs on the target line and the generation time of each inquiry log on the associated line; arranging the inquiry logs on the target line and the inquiry logs on each associated line according to the time sequence relation of the generation time to obtain a first on-line inquiry log cluster; deploying an online inquiry log database corresponding to the online inquiry event type through the first online inquiry log cluster; or; when the number of the inquiry logs on the associated lines is not less than two, acquiring first inquiry description information corresponding to the inquiry logs on the target line and second inquiry description information corresponding to each inquiry log on the associated line; performing diagnosis stage information mining on the first inquiry description information to obtain first diagnosis stage information of the inquiry logs on the target line, and performing diagnosis stage information mining on each second inquiry description information to obtain second diagnosis stage information of the inquiry logs on the corresponding associated line; the diagnosis stage information represents the generation sequence of the corresponding on-line inquiry logs; arranging the on-target line inquiry logs and the plurality of associated on-line inquiry logs according to the first diagnosis stage information and the second diagnosis stage information in a time sequence to obtain a second on-line inquiry log cluster; deploying an online inquiry log database corresponding to the online inquiry event type through the second online inquiry log cluster; or; when the number of the inquiry logs on the associated lines is not less than two, respectively acquiring the generation time of the inquiry logs on the target line and the generation time of each inquiry log on the associated line; determining a difference value of two random generation moments, and when the difference value meets a preset difference value, respectively performing diagnosis stage information mining on the inquiry logs on the target line and the inquiry logs on each associated line to obtain corresponding diagnosis stage information, wherein the diagnosis stage information represents a generation sequence of the corresponding inquiry logs on the line; arranging the inquiry logs on the target line and each inquiry log on the associated line according to the diagnosis stage information in a time sequence to obtain an inquiry log cluster on a third line; and deploying an online inquiry log database corresponding to the online inquiry event type through the third online inquiry log cluster.

2. The method of claim 1, wherein if the on-line inquiry logs corresponding to the on-line inquiry log database are classified as on-line inquiry logs having a periodic time-series association relationship, the obtaining N past on-line inquiry logs of the inquiry subjects associated with the target on-line inquiry log comprises:

acquiring inquiry description information corresponding to the inquiry log on the target line;

and if the on-line inquiry logs indicate that the target on-line inquiry logs are on-line inquiry logs with a stage time sequence incidence relation in a classified manner, acquiring N past on-line inquiry logs of inquiry objects associated with the target on-line inquiry logs, wherein N is more than or equal to 1.

3. The method of claim 1, wherein obtaining N temporary online interrogation logs from the N past online interrogation logs, wherein the N temporary online interrogation logs have an interrogation event commonality meeting an interrogation event commonality requirement, comprises:

determining the on-line inquiry logs of which the inquiry event commonality degree is within a preset range in the N on-line inquiry logs according to the inquiry event commonality degree of the target on-line inquiry log and each of the on-line inquiry logs;

4. The method of claim 1, wherein the sending the information associated with the online interrogation log database comprises:

5. A server, comprising a processor and a memory in communication with each other, the memory storing a program, the processor being configured to retrieve a computer program from the memory and to implement the method of any one of claims 1 to 4 by executing the computer program.

6. A storage medium having stored thereon a computer program which, when executed, performs the method of any one of claims 1 to 4.