CN113313463A

CN113313463A - Data analysis method and data analysis server applied to big data cloud office

Info

Publication number: CN113313463A
Application number: CN202110597631.6A
Authority: CN
Inventors: 姜康军; 邓云媛
Original assignee: Chuanglian Worry Free Guangzhou Information Technology Co ltd
Current assignee: Chuanglian Worry Free Guangzhou Information Technology Co ltd
Priority date: 2021-05-31
Filing date: 2021-05-31
Publication date: 2021-08-27

Abstract

The embodiment of the application discloses a data analysis method and a data analysis server applied to big data cloud office, wherein the data analysis method applied to big data cloud office comprises the following steps: the office process analysis is carried out on the office task data to be analyzed based on the pre-trained key process analysis model, so that corresponding topic feedback information is obtained based on different office processes, and task demand description is further generated, and therefore the office demand analysis condition of the target cloud office interaction terminal is determined. By the design, the difference between the topic feedback information in different office processes can be considered, and the acquired topic feedback information is ensured to have lower noise occupation ratio and higher topic heat, so that accurate office demand mining analysis can be realized, subsequent targeted office application and popularization are realized, and the waste of internet resources caused by a large amount of rough office application and popularization is reduced.

Description

Data analysis method and data analysis server applied to big data cloud office

Technical Field

The application relates to the technical field of big data and cloud office, in particular to a data analysis method and a data analysis server applied to big data cloud office.

Background

Big data (big data) is a data set which cannot be captured, managed and processed by a conventional software tool within a certain time range, and is a massive, high-growth rate and diversified information asset which can have stronger decision-making power, insight discovery power and flow optimization capability only by a new processing mode.

With the advent of the cloud computing/cloud business era, the fields related to big data are more and more extensive, such as cloud office, online finance, online retail, online cloud education and the like. Taking cloud office as an example, nowadays, enterprises mostly adopt a cloud office mode in order to improve work efficiency. However, in the cloud office process, how to deeply analyze the office requirements to realize subsequent accurate office application and popularization so as to reduce unnecessary waste of internet resources is a current difficulty.

Disclosure of Invention

One of the embodiments of the application provides a data analysis method applied to big data cloud office, the method is applied to a data analysis server and used for conducting office application and popularization on a target cloud office interactive terminal after the office demand analysis condition of the target cloud office interactive terminal is determined, and the method comprises the following steps:

acquiring office task data to be analyzed, and inputting the office task data to be analyzed into a key process analysis model;

performing office process analysis on the office task data to be analyzed through the key process analysis model to obtain an office process corresponding to the office task data to be analyzed;

and acquiring corresponding topic feedback information from the office task data to be analyzed according to the office progress, and generating task demand description according to the office progress and the topic feedback information so as to determine the office demand analysis condition of the target cloud office interactive terminal according to the task demand description.

Optionally, the key process analysis model includes a task screening model unit and an analysis model unit; the performing office process analysis on the office task data to be analyzed through the key process analysis model to obtain the office process corresponding to the office task data to be analyzed includes:

inputting the office task data to be analyzed into the task screening model unit to perform data screening processing and office process statistical processing so as to obtain office process description corresponding to the office task data to be analyzed;

inputting the office process description into the analysis model unit for office process analysis to obtain the cooperation record information of the office cooperation condition;

and determining an office progress corresponding to the office task data to be analyzed according to first preset office record information and the cooperation record information of the office cooperation condition.

Optionally, the task screening model unit includes an office resource identification layer, an office process classification layer and a statistical layer; the inputting the office task data to be analyzed into the task screening model unit for data screening processing and office process statistical processing to obtain office process descriptions corresponding to the office task data to be analyzed includes:

identifying each office operation node data in the office task data to be analyzed as a node resource description through the office resource identification layer;

performing office process analysis on the office task data to be analyzed through the office process classification layer, and performing project requirement analysis on office process labels corresponding to the obtained process analysis results to obtain office process requirement analysis results;

counting node resource description and office process demand analysis results corresponding to each office operation node data through the counting layer to obtain office theme statistical information corresponding to each office operation node data;

and determining the office process description corresponding to the office task data to be analyzed according to the office topic statistical information corresponding to all office operation node data in the office task data to be analyzed.

Optionally, the key process analysis model is obtained by training based on a thematic office task instruction set and thematic task evaluation information, wherein the thematic office task instruction set is an office task instruction set with inconsistent quantity of forward polarity thematic instructions and quantity of reverse polarity thematic instructions; the thematic task evaluation information is determined according to an office progress indication updating condition and a key office progress indication, wherein the key office progress indication is a key office progress indication corresponding to each office task indication in the thematic office task indication set, the office progress indication updating condition is an office progress indication updating condition corresponding to the office task indication obtained by using the key progress analytic model, and the thematic task evaluation information comprises a first evaluation topic, a second evaluation topic and updating time period information, and the method further comprises the following steps:

acquiring the special office task instruction set and key office progress instructions corresponding to the office task instructions in the special office task instruction set;

and training a key process analytic model to be trained according to the special office task instruction set and the key office process instruction to obtain the key process analytic model.

Optionally, the office task instruction set includes a plurality of office task instructions, and the to-be-trained key process analytic model includes a to-be-trained task screening model unit and a to-be-trained analytic model unit; the training a to-be-trained key process analytic model according to the office task instruction set and the key office process instruction to obtain the key process analytic model comprises the following steps:

performing data screening processing and office progress statistical processing on each office task instruction through the to-be-trained task screening model unit to obtain office progress description instructions corresponding to each office task instruction;

performing office process analysis on the office process description indication through the to-be-trained analysis model unit to obtain an office process indication updating condition;

and determining the thematic task evaluation information according to the office process instruction updating condition and the key office process instruction corresponding to each office task instruction, and adjusting the model performance index of the key process analytic model to be trained according to the thematic task evaluation information until the task evaluation error of the thematic task evaluation information is smaller than a set error or the training of set times is completed.

Optionally, the determining the thematic task evaluation information according to the office progress indication updating condition and the key office progress indication corresponding to each office task indication includes:

determining a first model performance index according to office progress indication updating conditions corresponding to the office task indications, office progress interference values in the key office progress indications and second preset office record information;

determining a second model performance index according to the delayed office progress of the first model performance index;

and generating the thematic task evaluation information according to the second model performance index, the office progress indication updating condition, the office progress interference value, the indication novelty parameter of the forward polarity thematic indication, the indication habitual parameter and the updating time period information.

Optionally, the generating the thematic task evaluation information according to the second model performance index, the office progress indication updating condition, the office progress interference value, the indication novelty parameter of the forward polarity thematic indication, the indication habituation parameter, and the updating period information includes:

generating the first evaluation topic according to the second model performance index, the office progress indication updating condition, the office progress interference value and the indication novelty parameter of the forward polarity topic indication;

generating the second evaluation subject according to the second model performance index, the office progress indication updating condition, the office progress interference value, the indication novelty parameter indicated by the forward polarity subject and the indication habitual parameter;

and generating the thematic task evaluation information according to the first evaluation topic, the second evaluation topic and the updating time period information.

Optionally, obtaining corresponding topic feedback information from the office task data to be analyzed according to the office process includes:

acquiring first office task data and second office task data corresponding to office task data to be analyzed according to a task allocation strategy corresponding to the office process, wherein the first office task data comprises interactive task data which do not contain office task management labels in the office task data to be analyzed, and the second office task data comprises interactive task data which contain office task management labels in the office task data to be analyzed;

performing operation preference description extraction on the first office task data to obtain non-explicit preference description corresponding to the first office task data; performing operation preference description extraction on the second office task data to obtain explicit preference description corresponding to the second office task data;

performing description splicing on the explicit preference description and the non-explicit preference description based on operation heat to obtain task topic description corresponding to the office task data to be analyzed; grouping the task topics to the task topic description to obtain a grouping result corresponding to the office task data to be analyzed; under the condition that the grouping result meets a preset topic feedback detection condition, acquiring office task data matched with the grouping label from the office task data to be analyzed through the grouping label indicated by the grouping result to serve as the topic feedback information;

the acquiring of the first office task data and the second office task data corresponding to the office task data to be analyzed according to the task allocation strategy corresponding to the office process includes:

according to a task allocation strategy corresponding to the office process, performing office task interaction detection on the office task data to be analyzed to obtain first interactive task data which do not include an office task management label in the office task data to be analyzed, and performing data statistics processing aiming at task event types on the first interactive task data in the office task data to be analyzed to serve as the first office task data; according to the first interactive task data, second office task recorded data containing office task management labels in the office task data to be analyzed are obtained, and the second office task recorded data in the office task data to be analyzed are subjected to data statistics processing aiming at task event types and serve as the second office task data;

wherein the extracting of the operation preference description of the first office task data to obtain the non-explicit preference description corresponding to the first office task data includes:

calling a first operation preference description analysis layer in a preset preference description extraction network, and performing operation preference description extraction on the first office task data to obtain a non-explicit preference description corresponding to the first office task data;

wherein the extracting of the operation preference description of the second office task data to obtain an explicit preference description corresponding to the second office task data includes:

calling a second operation preference description analysis layer in the preset preference description extraction network, and performing operation preference description extraction on the second office task data to obtain an explicit preference description corresponding to the second office task data;

the operation-heat-based description splicing is performed on the explicit preference description and the non-explicit preference description to obtain the task topic description corresponding to the office task data to be analyzed, and the operation-heat-based description splicing includes:

calling a preference description splicing layer in the preset preference description extraction network, and performing operation heat-based description splicing on the explicit preference description and the non-explicit preference description to obtain task topic descriptions corresponding to the office task data to be analyzed;

the task topic grouping is performed on the task topic description to obtain a grouping result corresponding to the office task data to be analyzed, and the grouping result comprises the following steps:

calling a preference description grouping layer in the preset preference description extraction network, and grouping the task topics to obtain a grouping result corresponding to the office task data to be analyzed;

under the condition that the grouping result meets a preset topic feedback detection condition, acquiring office task data matched with the grouping label from the office task data to be analyzed through the grouping label indicated by the grouping result to serve as the topic feedback information, wherein the topic feedback information comprises:

acquiring key task topic associated information of the grouping result; respectively performing active comment state analysis and cold visit state analysis on topic associated elements of a plurality of task topic associated information in the key task topic associated information to obtain analysis results corresponding to the active comment states and analysis results corresponding to the cold comment states;

performing trending topic information optimization processing on an analysis result corresponding to the active comment state through a preset trending topic information optimization mode to obtain a trending task topic associated information set comprising the active comment state; performing cold topic information optimization processing on an analysis result corresponding to the cold comment state through a preset cold topic information optimization mode to obtain a cold task topic associated information set comprising the cold comment state;

performing topic feedback heat analysis based on the hot task topic associated information set and the cold task topic associated information set to obtain a topic heat detection index matched with a target behavior state in the key task topic associated information; the target behavior state comprises at least one of an active comment state and a cold comment state;

and if the heat detection result represents that the key task topic associated information corresponds to a topic feedback hot state, acquiring office task data matched with the active comment state from the office task data to be analyzed in the active comment state corresponding to a grouping label indicated by the grouping result as the topic feedback information.

Optionally, generating a task demand description according to the office process and the topic feedback information, so as to determine an office demand analysis condition of the target cloud office interaction terminal according to the task demand description, including:

acquiring positive feedback data and negative feedback data in the topic feedback information according to the office task category information corresponding to the office process; based on the feedback heat degree change between the positive feedback data and the negative feedback data in the topic feedback information, performing office demand analysis on the positive feedback data and the negative feedback data in the topic feedback information to obtain a demand content analysis result;

determining the negative feedback data with abnormality in office demand analysis as to-be-matched negative feedback data, and determining office demand characteristics matched with the to-be-matched negative feedback data according to the similarity between the negative feedback data in the demand content analysis result and the to-be-matched negative feedback data; performing office demand analysis on the office demand characteristics matched with the to-be-matched passive feedback data and the to-be-matched passive feedback data to obtain a key demand analysis result; determining task demand description in the topic feedback information and topic content distribution corresponding to the task demand description according to the key demand analysis result and the demand content analysis result; wherein the topic content distribution comprises different office response preferences corresponding to the task demand description;

according to the task demand office record information and the corresponding topic content distribution thereof, adopting a preset demand analysis algorithm to carry out office demand mining analysis on the target cloud office interaction terminal, so as to obtain the office demand analysis condition; wherein the preset demand analysis algorithm comprises: a decision tree algorithm, a rule induction algorithm, a case-based learning algorithm, a discriminant algorithm, or a cluster analysis algorithm.

The second embodiment of the present application provides a data analysis server, which includes a processing engine, a network module and a memory; the processing engine and the memory communicate through the network module, and the processing engine reads the computer program from the memory and operates to perform the above-described method.

In the description that follows, additional features will be set forth, in part, in the description. 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

The present application will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:

FIG. 1 is a flow diagram illustrating an exemplary data analysis method and/or process for big data cloud office applications, according to some embodiments of the invention;

FIG. 2 is a block diagram of an exemplary data analysis device for big data cloud office applications, according to some embodiments of the present invention;

FIG. 3 is a block diagram of an exemplary data analysis system for big data cloud office, according to some embodiments of the invention, an

FIG. 4 is a diagram illustrating the hardware and software components of an exemplary data analysis server, according to some embodiments of the invention.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only examples or embodiments of the application, from which the application can also be applied to other similar scenarios without inventive effort for a person skilled in the art. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "device", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this application and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

The inventor finds, through research and analysis, that the office demand analysis condition is inaccurate in the process of performing office demand analysis on an office task, and the reason for this is that differences among different office processes of the office task and corresponding topic feedback information under different office processes are not considered, and meanwhile, when the topic feedback information is obtained, more interference information may be introduced, so that when task demand description is determined, the characteristic resolution of the task demand description is affected.

In order to solve the problems, the inventor provides a data analysis method and a data analysis server applied to big data cloud office in a targeted manner, and by analyzing office processes of office task data to be analyzed and considering differences among topic feedback information in different office processes, the obtained topic feedback information is ensured to have a low noise ratio, so that accurate office demand analysis can be realized, subsequent targeted office application and popularization can be realized, and waste of internet resources caused by a large amount of rough office application and popularization can be reduced.

First, an exemplary description is given to a data analysis method applied to a big data cloud office, please refer to fig. 1, which is a flowchart of an exemplary data analysis method and/or process applied to a big data cloud office according to some embodiments of the present invention, where the data analysis method applied to a big data cloud office may be applied to a data analysis server, so as to perform office application and popularization to a target cloud office interaction terminal after determining an office demand analysis condition of the target cloud office interaction terminal, and further, the method may include the following technical solutions described in steps S11 to S13.

And step S11, acquiring office task data to be analyzed, and inputting the office task data to be analyzed into a key process analysis model.

In this embodiment, the office task data to be analyzed can be acquired from the target cloud office interactive terminal. Before acquiring office task data to be analyzed from the target cloud office interactive terminal, the data analysis server can firstly obtain authorization of the target cloud office interactive terminal, and the data analysis server cannot participate in office tasks of the target cloud office interactive terminal, so that mutual independence between different cloud office interactive terminals during office task interaction can be guaranteed. That is, the data analysis server is only used for carrying out office demand analysis on the office task data of the cloud office interaction terminal. Furthermore, the office task data to be analyzed comprises various data of the target cloud office interaction terminal during office tasks, which are not listed herein.

In this embodiment, the data analysis server may be a cloud service platform, and the cloud office interaction terminal may be an intelligent electronic device, including but not limited to a smart phone, a tablet computer, and a notebook computer. Further, the office task data to be analyzed can be real-time office task data of the target cloud office interaction terminal.

In this embodiment, the key process analytic model may be a convolutional neural model trained in advance, and a model performance adjustment process of the training process may be adjusted according to an actual task requirement, for example, a corresponding training set is selected in advance for training, and for example, a convergence condition of the network model is set in advance. The analysis method can be understood that the key process analysis model is used for carrying out thematic and real-time office process analysis on the office task data to be analyzed so as to ensure the follow-up timeliness in office demand analysis and avoid the problem that the office demand analysis result has deviation due to lag in office demand analysis.

Further, the embodiment of the invention also provides a training process for the key process analytic model, wherein the key process analytic model is obtained by training based on a thematic office task instruction set and thematic task evaluation information, and the thematic office task instruction set is an office task instruction set with inconsistent quantity of positive polarity thematic instructions and quantity of reverse polarity thematic instructions; and the thematic task evaluation information is determined according to the office progress indication updating condition and the key office progress indication.

Furthermore, the key office process instruction is a key office process instruction corresponding to each office task instruction in the special office task instruction set, the office process instruction update condition is an office process instruction update condition corresponding to the office task instruction acquired by using the key process analysis model, and the special task evaluation information includes a first evaluation topic, a second evaluation topic and update period information.

Based on the above, before step S11, the key process analytic model may be trained in advance, and the training process of the key process analytic model includes the following steps a and b.

Step a, acquiring the special office task instruction set and key office progress instructions corresponding to the office task instructions in the special office task instruction set.

And b, training a key process analytic model to be trained according to the special office task instruction set and the key office process instruction to obtain the key process analytic model.

On the basis of the above content, the office task instruction set includes a plurality of office task instructions, the to-be-trained key process analytic model includes a to-be-trained task screening model unit and a to-be-trained analytic model unit, and step b can also be implemented in the following manner: performing data screening processing and office progress statistical processing on each office task instruction through the to-be-trained task screening model unit to obtain office progress description instructions corresponding to each office task instruction; performing office process analysis on the office process description indication through the to-be-trained analysis model unit to obtain an office process indication updating condition; and determining the thematic task evaluation information according to the office process instruction updating condition and the key office process instruction corresponding to each office task instruction, and adjusting the model performance index of the key process analytic model to be trained according to the thematic task evaluation information until the task evaluation error of the thematic task evaluation information is smaller than a set error or the training of set times is completed.

In this embodiment, the office progress indication update condition may be recorded in a form of a list, or may be recorded in a form of an image curve, which is not limited herein, and the task evaluation error is used to represent an error condition of task evaluation of the thematic task evaluation information in the evaluation process. The office task indication may represent information of the aspects of rationality, real-time performance, legality, and the like of the office task, and is not described herein again.

On the basis of the above content, the determining the thematic task evaluation information according to the office progress indication updating condition and the key office progress indication corresponding to each office task indication includes: determining a first model performance index according to office progress indication updating conditions corresponding to the office task indications, office progress interference values in the key office progress indications and second preset office record information; determining a second model performance index according to the delayed office progress of the first model performance index; and generating the thematic task evaluation information according to the second model performance index, the office progress indication updating condition, the office progress interference value, the indication novelty parameter of the forward polarity thematic indication, the indication habitual parameter and the updating time period information.

In this embodiment, the model performance index may be understood as a network parameter of the model network, the parameter indicating novelty (timeliness or update degree) may be a novelty weight, the parameter indicating habituation may be an operation habit of different indexes in different time periods, and the office process interference value may be used to represent interference of different office processes on other office processes.

Further, the generating the thematic task evaluation information according to the second model performance index, the office progress indication updating condition, the office progress interference value, the indication novelty parameter of the forward polarity thematic indication, the indication habitual parameter and the updating time period information includes: generating the first evaluation topic according to the second model performance index, the office progress indication updating condition, the office progress interference value and the indication novelty parameter of the forward polarity topic indication; generating the second evaluation subject according to the second model performance index, the office progress indication updating condition, the office progress interference value, the indication novelty parameter indicated by the forward polarity subject and the indication habitual parameter; and generating the thematic task evaluation information according to the first evaluation topic, the second evaluation topic and the updating time period information.

In this embodiment, the evaluation topic may be a topic corresponding to a lot of attention to the office task, and related office dimension information of the remote online task, such as object information, region information, access mode information, and office software update information, is recorded in the evaluation topic, which is not described herein again.

It can be understood that, by implementing the contents described in the above steps a and b, the training of the key process analytic model can be realized in advance, so as to ensure the operation stability, generalization capability and analytic accuracy of the key process analytic model.

And step S12, performing office process analysis on the office task data to be analyzed through the key process analysis model to obtain the office process corresponding to the office task data to be analyzed.

In this embodiment, there are a plurality of office processes corresponding to the office task data to be analyzed, for example, the office process 1 (graphics context operation process in the office task), the office process 2 (optimization operation process in the office task), or the office process 3 (backup process for the office task), and the like, which are not limited herein, it can be understood that, in different office processes, the topic feedback information may be different, and by performing analysis on different office processes on the task data to be analyzed, different topic feedback information can be distinguished as much as possible, thereby comprehensively implementing analysis and mining of task requirement description.

In this embodiment, the key process analysis model includes a task screening model unit and an analysis model unit, and the task screening model unit and the analysis model unit may be a functional network layer in the key process analysis model, and further, step S2 may be implemented by: inputting the office task data to be analyzed into the task screening model unit to perform data screening processing and office process statistical processing so as to obtain office process description corresponding to the office task data to be analyzed; inputting the office process description into the analysis model unit for office process analysis to obtain the cooperation record information of the office cooperation condition; and determining an office progress corresponding to the office task data to be analyzed according to first preset office record information and the cooperation record information of the office cooperation condition.

In this embodiment, the office progress descriptions may be descriptions formed by screening according to the office sequence, the collaboration recorded information is information for describing the office collaboration situation recorded in the collaboration mode, and the traceability of the office collaboration situation can be ensured by recording the office progress information in an assistance mode, and the first preset office recorded information may be determined according to the historical office progress. By the design, through the mutual matching between the task screening model unit and the analysis model unit, different office processes corresponding to the office task data to be analyzed can be accurately and completely determined.

It can be understood that the task screening model unit may further include a plurality of functional layers corresponding to existence of logical continuity, for example, the task screening model unit may further include an office resource identification layer, an office process classification layer, a statistical layer, and the like, based on which the above description that the office task data to be analyzed is input to the task screening model unit for data screening processing and office process statistical processing to obtain the office process description corresponding to the office task data to be analyzed includes: identifying each office operation node data in the office task data to be analyzed as a node resource description through the office resource identification layer; performing office process analysis on the office task data to be analyzed through the office process classification layer, and performing project requirement analysis on office process labels corresponding to the obtained process analysis results to obtain office process requirement analysis results; counting node resource description and office process demand analysis results corresponding to each office operation node data through the counting layer to obtain office theme statistical information corresponding to each office operation node data; and determining the office process description corresponding to the office task data to be analyzed according to the office topic statistical information corresponding to all office operation node data in the office task data to be analyzed.

In the above, the office progress tags are used to distinguish between different office progresses. In actual implementation, office operation node data is screened, then office progress analysis of office task data to be analyzed is performed in parallel, and a corresponding office progress demand analysis result is obtained, so that office topic statistical information can be further determined, wherein the office topic statistical information can be realized based on a Kmeans clustering algorithm. By the design, independence of the office process descriptions can be ensured.

Step S13, acquiring corresponding topic feedback information from the office task data to be analyzed according to the office progress, and generating task demand description according to the office progress and the topic feedback information so as to determine the office demand analysis condition of the target cloud office interaction terminal according to the task demand description.

In this embodiment, the topic feedback information may be key topic information extracted from the office task data to be analyzed, and is displayed in a form of characters or images, and in an actual implementation process, the inventor finds that it is important for generating task requirement description and subsequent task requirement analysis to accurately extract the topic feedback information, and to achieve this purpose, the topic feedback information obtained from the office task data to be analyzed according to the office process may include the contents described in the following steps S131 to S133.

Step S131, acquiring first office task data and second office task data corresponding to office task data to be analyzed according to a task allocation strategy corresponding to the office process, wherein the first office task data comprises interactive task data which does not include an office task management tag in the office task data to be analyzed, and the second office task data comprises interactive task data which includes an office task management tag in the office task data to be analyzed. In this embodiment, the office task management tag may be used to distinguish different office task behaviors, for example, "D" may represent a completed office task, "S" may represent an unfinished office task, "C" may represent an office task to be distributed, and further, the office task management tag may also be represented in other manners, which is not limited herein, and the interactive task data is used to represent that there are mutual transmission and usage behaviors between task data.

In this embodiment, acquiring the first office task data and the second office task data corresponding to the office task data to be analyzed according to the task allocation policy corresponding to the office process further includes: according to a task allocation strategy corresponding to the office process, performing office task interaction detection on the office task data to be analyzed to obtain first interactive task data which do not include an office task management label in the office task data to be analyzed, and performing data statistics processing aiming at task event types on the first interactive task data in the office task data to be analyzed to serve as the first office task data; and acquiring second office task recorded data containing an office task management label in the office task data to be analyzed according to the first interactive task data, and performing data statistics processing aiming at task event types on the second office task recorded data in the office task data to be analyzed to serve as the second office task data.

Step S132, performing operation preference description extraction on the first office task data to obtain a non-explicit preference description corresponding to the first office task data; and performing operation preference description extraction on the second office task data to obtain explicit preference description corresponding to the second office task data. In this embodiment, the operation preference description extracting operation may be an operation of extracting task data according to the popularity of the preference description, the non-explicit preference description may be understood as an implicit preference description of the user, for example, a preference description for system analysis, and the explicit preference description may be understood as an explicit preference description of the user.

In this embodiment, the extracting the operation preference description of the first office task data to obtain a non-explicit preference description corresponding to the first office task data includes: and calling a first operation preference description analysis layer in a preset preference description extraction network, and performing operation preference description extraction on the first office task data to obtain the non-explicit preference description corresponding to the first office task data. The extracting of the operation preference description of the second office task data to obtain the explicit preference description corresponding to the second office task data includes: and calling a second operation preference description analysis layer in the preset preference description extraction network, and performing operation preference description extraction on the second office task data to obtain an explicit preference description corresponding to the second office task data.

Step S133, performing description splicing on the explicit preference description and the non-explicit preference description based on operation heat to obtain task topic descriptions corresponding to the office task data to be analyzed; grouping the task topics to the task topic description to obtain a grouping result corresponding to the office task data to be analyzed; and under the condition that the grouping result meets a preset topic feedback detection condition, acquiring office task data matched with the grouping label from the office task data to be analyzed through the grouping label indicated by the grouping result to serve as the topic feedback information. In the embodiment, the operation heat can reflect the related information of the task topic to a certain extent, and by designing such that based on the steps S131 to S133, the topic feedback information can be accurately extracted, so as to provide an accurate data basis for the generation of the subsequent task requirement description and the subsequent requirement analysis.

In this embodiment, the performing operation-heat-based description splicing on the explicit preference description and the non-explicit preference description to obtain the task topic description corresponding to the office task data to be analyzed includes: and calling a preference description splicing layer in the preset preference description extraction network, and performing operation heat-based description splicing on the explicit preference description and the non-explicit preference description to obtain task topic descriptions corresponding to the office task data to be analyzed.

In this embodiment, in the case that the grouping result satisfies the preset topic feedback detection condition as described in step S133, acquiring office task data matching the grouping tag from the office task data to be analyzed through the grouping tag indicated by the grouping result as the topic feedback information, and further may include the contents described in the following steps S1331 to S1334.

Step S1331, obtaining key task topic associated information of the grouping result; and respectively carrying out active comment state analysis and cold visit state analysis on topic associated elements of a plurality of task topic associated information in the key task topic associated information to obtain analysis results corresponding to the active comment states and analysis results corresponding to the cold comment states.

Step S1332, carrying out hot topic information optimization processing on the analysis result corresponding to the active comment state through a preset hot topic information optimization mode to obtain a hot task topic association information set including the active comment state; and performing cold topic information optimization processing on the analysis result corresponding to the cold comment state through a preset cold topic information optimization mode to obtain a cold task topic associated information set comprising the cold comment state.

In this embodiment, the preset hot topic information optimization manner may be an optimization manner formulated in advance according to a hot topic, the hot topic may be understood as a topic with a higher occurrence frequency in the task discussion, and the cold topic may be understood as a topic with a lower occurrence frequency in the task discussion, and it may be understood that the hot task topic association information set and the cold task topic association information set are also relative to each other.

Step S1333, performing topic feedback heat analysis based on the hot task topic associated information set and the cold task topic associated information set to obtain a topic heat detection index matched with a target behavior state in the key task topic associated information; the target behavioral state includes at least one of an active review state and a cold review state.

In this embodiment, the topic popularity detection index is used for detecting topic popularity of the key task topic associated information, so that accurate acquisition of topic feedback information is realized.

Step S1334, carrying out topic popularity detection on the key task topic associated information according to the topic popularity detection index to obtain a topic popularity detection result, and if the popularity detection result represents that the key task topic associated information corresponds to a topic feedback popularity state, acquiring office task data matched with the active comment state from the office task data to be analyzed in the active comment state corresponding to a grouping label indicated by the grouping result as the topic feedback information.

In this embodiment, when topic feedback information is acquired from office task data to be analyzed, topic popularity is considered, so that the acquired topic feedback information can be ensured to have higher topic popularity, that is, an accurate data basis is provided for subsequent task demand analysis, and the acquisition of relatively cold topic feedback information is avoided as far as possible, thereby avoiding the deviation of subsequent task demand analysis.

Further, in order to quickly and flexibly determine the office demand analysis situation of the target cloud office interaction terminal, the task demand description generated according to the office progress and the topic feedback information in step S13 may include the following contents: acquiring positive feedback data and negative feedback data in the topic feedback information according to the office task category information corresponding to the office process; based on the feedback heat degree change between the positive feedback data and the negative feedback data in the topic feedback information, performing office demand analysis on the positive feedback data and the negative feedback data in the topic feedback information to obtain a demand content analysis result; determining the negative feedback data with abnormality in office demand analysis as to-be-matched negative feedback data, and determining office demand characteristics matched with the to-be-matched negative feedback data according to the similarity between the negative feedback data in the demand content analysis result and the to-be-matched negative feedback data; performing office demand analysis on the office demand characteristics matched with the to-be-matched passive feedback data and the to-be-matched passive feedback data to obtain a key demand analysis result; determining task demand description in the topic feedback information and topic content distribution corresponding to the task demand description according to the key demand analysis result and the demand content analysis result; wherein the topic content distribution comprises different office response preferences corresponding to the task demand description; and according to the task demand office record information and the corresponding topic content distribution thereof, adopting a preset demand analysis algorithm to carry out office demand mining analysis on the target cloud office interactive terminal, so as to obtain the office demand analysis condition.

In this embodiment, alternatively, the acquiring of the positive feedback data and the negative feedback data in the topic feedback information further includes: acquiring at least two positive feedback content descriptions and at least two negative feedback content descriptions in the topic feedback information; acquiring explicit relevance between the at least two positive feedback content descriptions and office user difference information of the positive feedback content descriptions, and acquiring implicit relevance between the at least two negative feedback content descriptions and office user difference information of the negative feedback content descriptions; according to the explicit relevance and office user difference information described by the positive feedback content, performing description statistics on the at least two positive feedback content descriptions to obtain positive feedback data in the topic feedback information; one positive feedback data includes at least one positive feedback content description; according to the implicit relevance and the office user difference information described by the passive feedback content, performing description statistics on the at least two passive feedback content descriptions to obtain passive feedback data in the topic feedback information; one negative feedback data comprises at least one negative feedback content description.

In this embodiment, alternatively, the performing office demand analysis on the positive feedback data and the negative feedback data in the topic feedback information based on the feedback heat degree change between the positive feedback data and the negative feedback data in the topic feedback information to obtain a demand content analysis result includes: determining negative feedback data in the topic feedback information as topic negative feedback data, and determining positive feedback data in the topic feedback information as topic positive feedback data; the negative feedback content description in the topical negative feedback data is determined from an operational function call record for the topical feedback information; acquiring positive feedback content description in the operation function call record; determining content description relevance between positive feedback content description in the operation function call record and positive feedback content description in the thematic positive feedback data as the feedback heat degree change between the thematic negative feedback data and the thematic positive feedback data; and when the change rate corresponding to the change of the feedback heat degree is greater than or equal to a preset change rate threshold value, carrying out office demand analysis on the thematic negative feedback data and the thematic positive feedback data to obtain a demand content analysis result. By the design, the integrity and the real-time performance of the required content analysis result can be ensured.

In this embodiment, alternatively, the to-be-matched negative feedback data includes a first negative feedback content description in the topic feedback information; the number of the required content analysis results is at least two; the negative feedback data in each demand content analysis result respectively comprises a second negative feedback content description in the topic feedback information; the determining the office demand characteristics matched with the to-be-matched negative feedback data according to the similarity between the negative feedback data in the demand content analysis result and the to-be-matched negative feedback data comprises the following steps: acquiring a first negative data characteristic of the negative feedback data to be matched according to the first negative feedback content description; respectively acquiring second negative data characteristics of the negative feedback data in each demand content analysis result according to the second negative feedback content description included in each demand content analysis result; acquiring data comparison results between the first negative data characteristics and second negative data characteristics corresponding to each demand content analysis result respectively; according to the data comparison result to which each required content analysis result belongs, determining the similarity between the negative feedback data in each required content analysis result and the to-be-matched negative feedback data; when the number of the target demand content analysis results is larger than a first preset number value and smaller than or equal to a second preset number value, determining the office demand characteristics contained in the positive feedback data in the target demand content analysis results as the office demand characteristics matched with the to-be-matched negative feedback data; the target demand content analysis result refers to a demand content analysis result of which the similarity is greater than or equal to a preset popularity threshold.

On the basis of the above, further, the number of content descriptions of the first negative feedback content description is at least two; the acquiring of the first negative data characteristic of the to-be-matched negative feedback data according to the first negative feedback content description comprises: acquiring content description abnormal features respectively corresponding to each first negative feedback content description in at least two first negative feedback content descriptions; acquiring first key abnormal features corresponding to the at least two first negative feedback content descriptions according to the content description abnormal features respectively corresponding to each first negative feedback content description; determining the first key abnormal feature as the first negative data feature.

In this embodiment, the preset demand analysis algorithm includes: a decision tree algorithm, a rule induction algorithm, a case-based learning algorithm, a discriminant algorithm, or a cluster analysis algorithm. Furthermore, statistical algorithms and neural network algorithms may be included. Further, the statistical algorithm may include regression analysis (multiple regression, auto regression, etc.), discriminant analysis (bayesian discriminant, etc.). Further, the cluster analysis algorithm may include systematic clustering, topic clustering, and the like. In practical applications, the mining algorithms described above may be used in combination, and are not limited herein.

On the basis of the above-mentioned step S11-step S13, the contents described in the following step S13 may be further included. And step S14, determining a task popularization strategy of the target cloud office interaction terminal according to the office demand analysis condition, and carrying out office application popularization according to the task popularization strategy.

In this embodiment, the task promotion strategy may include the type of application to be promoted and the promotion period of the office application, and by such a design, the efficiency of the office application promotion can be ensured as much as possible, and the phenomenon that too many internet resources are occupied due to repeated promotion is avoided.

In summary, the data analysis method and the data analysis server applied to the big data cloud office provided by the embodiment of the invention can perform office process analysis on office task data to be analyzed based on a pre-trained key process analysis model, so that corresponding topic feedback information is obtained based on different office processes, and task requirement description is further generated, so as to determine the office requirement analysis condition of the target cloud office interaction terminal. Therefore, the difference between the topic feedback information in different office processes can be considered, and the obtained topic feedback information is ensured to have lower noise occupation ratio and higher topic heat, so that accurate office task demand analysis can be realized, subsequent targeted office application and popularization are realized, and the waste of internet resources caused by a large amount of rough office application and popularization is reduced.

With respect to the above-described steps S11 to S14, the description can be made by summarizing: the method comprises the steps of inputting acquired office task data to be analyzed into a key process analysis model to obtain a corresponding office process, mining and analyzing office demands of a target cloud office interaction terminal according to the office process to obtain an office demand analysis condition, determining a task popularization strategy of the target cloud office interaction terminal according to the office demand analysis condition, and carrying out office application popularization according to the task popularization strategy; the target cloud office interaction terminal corresponds to the office task data to be analyzed.

Further, the acquired office task data to be analyzed is input into the key process analysis model to obtain a corresponding office process, and the office demand mining analysis of the target cloud office interaction terminal is realized according to the office process to obtain the office demand analysis condition, which may include: acquiring office task data to be analyzed, and inputting the office task data to be analyzed into a key process analysis model; performing office process analysis on the office task data to be analyzed through the key process analysis model to obtain an office process corresponding to the office task data to be analyzed; and acquiring corresponding topic feedback information from the office task data to be analyzed according to the office progress, and generating task demand description according to the office progress and the topic feedback information so as to determine the office demand analysis condition of the target cloud office interactive terminal according to the task demand description.

It should be understood that further description of the above summary can refer to the description of step S11-step S14, which is not repeated herein.

Next, for the data analysis method applied to the big data cloud office, an exemplary data analysis device applied to the big data cloud office is further provided in the embodiment of the present invention, and as shown in fig. 2, the data analysis device 200 applied to the big data cloud office may include the following functional modules.

The data obtaining module 210 is configured to obtain office task data to be analyzed, and input the office task data to be analyzed into a key process analysis model.

And the process analysis module 220 is configured to perform office process analysis on the office task data to be analyzed through the key process analysis model, so as to obtain an office process corresponding to the office task data to be analyzed.

The requirement analysis module 230 is configured to obtain corresponding topic feedback information from the office task data to be analyzed according to the office process, and generate a task requirement description according to the office process and the topic feedback information, so as to determine an office requirement analysis condition of the target cloud office interaction terminal according to the task requirement description.

Then, based on the above method embodiment and apparatus embodiment, the embodiment of the present invention further provides a system embodiment, that is, a data analysis system applied to big data cloud office, please refer to fig. 3, and a data analysis system 30 applied to big data cloud office may include a data analysis server 10 and a cloud office interactive terminal 20. The data analysis server 10 and the cloud office interactive terminal 20 are in communication to implement the above method, and further, the functionality of the data analysis system 30 applied to the big data cloud office is described as follows.

A data analysis system applied to big data cloud office comprises a data analysis server and a cloud office interaction terminal which are communicated with each other, wherein the data analysis server is used for: acquiring office task data to be analyzed, and inputting the office task data to be analyzed into a key process analysis model; performing office process analysis on the office task data to be analyzed through the key process analysis model to obtain an office process corresponding to the office task data to be analyzed; acquiring corresponding topic feedback information from the office task data to be analyzed according to the office process, generating task demand description according to the office process and the topic feedback information, determining the office demand analysis condition of the target cloud office interaction terminal according to the task demand description, determining the task popularization strategy of the target cloud office interaction terminal according to the office demand analysis condition, and performing office application and popularization according to the task popularization strategy.

Further, referring to fig. 4 in conjunction, the data analysis server 10 may include a processing engine 110, a network module 120, and a memory 130, the processing engine 110 and the memory 130 communicating through the network module 120.

Processing engine 110 may process the relevant information and/or data to perform one or more of the functions described herein. For example, in some embodiments, processing engine 110 may include at least one processing engine (e.g., a single core processing engine or a multi-core processor). By way of example only, the Processing engine 110 may include a Central Processing Unit (CPU), an Application-Specific Integrated Circuit (ASIC), an Application-Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.

Network module 120 may facilitate the exchange of information and/or data. In some embodiments, the network module 120 may be any type of wired or wireless network or combination thereof. Merely by way of example, the Network module 120 may include a cable Network, a wired Network, a fiber optic Network, a telecommunications Network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a bluetooth Network, a Wireless personal Area Network, a Near Field Communication (NFC) Network, and the like, or any combination thereof. In some embodiments, the network module 120 may include at least one network access point. For example, the network module 120 may include wired or wireless network access points, such as base stations and/or network access points.

The Memory 130 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 130 is used for storing a program, and the processing engine 110 executes the program after receiving the execution instruction.

It will be appreciated that the configuration shown in fig. 4 is merely illustrative and that the data analysis server 10 may include more or fewer components than shown in fig. 2 or may have a different configuration than shown in fig. 4. The components shown in fig. 4 may be implemented in hardware, software, or a combination thereof.

It should be understood that, for the above, a person skilled in the art can deduce from the above disclosure to determine the meaning of the related technical term without doubt, for example, for some values, coefficients, weights, indexes, factors, and other terms, a person skilled in the art can deduce and determine from the logical relationship between the above and the following, and the value range of these values can be selected according to the actual situation, for example, 0 to 1, for example, 1 to 10, and for example, 50 to 100, which are not limited herein.

The skilled person can unambiguously determine some preset, reference, predetermined, set and target technical features/terms, such as threshold values, threshold intervals, threshold ranges, etc., from the above disclosure. For some technical characteristic terms which are not explained, the technical solution can be clearly and completely implemented by those skilled in the art by reasonably and unambiguously deriving the technical solution based on the logical relations in the previous and following paragraphs. Prefixes of unexplained technical feature terms, such as "first", "second", "previous", "next", "current", "history", "latest", "best", "target", "specified", and "real-time", etc., can be unambiguously derived and determined from the context. Suffixes of technical feature terms not to be explained, such as "list", "feature", "sequence", "set", "matrix", "unit", "element", "track", and "list", etc., can also be derived and determined unambiguously from the foregoing and the following.

The foregoing disclosure of embodiments of the present invention will be apparent to those skilled in the art. 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.

It should be appreciated that the system and its modules shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).

It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered 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.

Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.

Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.

The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.

Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the numbers allow for adaptive variation. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. A data analysis method applied to big data cloud office is characterized in that the method is applied to a data analysis server and used for conducting office application promotion on a target cloud office interactive terminal after the office demand analysis condition of the target cloud office interactive terminal is determined, and the method comprises the following steps:

2. The method of claim 1, wherein the key process analytic model comprises a task screening model unit and an analytic model unit; the performing office process analysis on the office task data to be analyzed through the key process analysis model to obtain the office process corresponding to the office task data to be analyzed includes:

3. The method of claim 2, wherein the task screening model unit comprises an office resource identification layer, an office process classification layer and a statistical layer; the inputting the office task data to be analyzed into the task screening model unit for data screening processing and office process statistical processing to obtain office process descriptions corresponding to the office task data to be analyzed includes:

4. The method according to claim 1, wherein the key process analytic model is trained based on a thematic office task instruction set and thematic task evaluation information, wherein the thematic office task instruction set is an office task instruction set with inconsistent forward polarity thematic instruction number and reverse polarity thematic instruction number; the thematic task evaluation information is determined according to an office progress indication updating condition and a key office progress indication, wherein the key office progress indication is a key office progress indication corresponding to each office task indication in the thematic office task indication set, the office progress indication updating condition is an office progress indication updating condition corresponding to the office task indication obtained by using the key progress analytic model, and the thematic task evaluation information comprises a first evaluation topic, a second evaluation topic and updating time period information, and the method further comprises the following steps:

5. The method according to claim 4, wherein the office task instruction set comprises a plurality of office task instructions, and the to-be-trained key process analytic model comprises a to-be-trained task screening model unit and a to-be-trained analytic model unit; the training a to-be-trained key process analytic model according to the office task instruction set and the key office process instruction to obtain the key process analytic model comprises the following steps:

6. The method according to claim 5, wherein the determining the thematic task assessment information according to the office progress indication updating condition and the key office progress indication corresponding to each office task indication comprises:

7. The method according to claim 6, wherein the generating the thematic task assessment information according to the second model performance index, the office progress indication update condition, the office progress interference value, the indication novelty parameter of forward polarity thematic indication, the indication habituation parameter and the update period information comprises:

8. The method as claimed in claim 1, wherein obtaining corresponding topic feedback information from the office task data to be analyzed according to the office process comprises:

9. The method according to claim 8, wherein generating a task demand description according to the office process and the topic feedback information to determine an office demand analysis situation of the target cloud office interactive terminal according to the task demand description comprises:

according to the task demand office record information and the corresponding topic content distribution thereof, adopting a preset demand analysis algorithm to carry out office demand mining analysis on the target cloud office interaction terminal, so as to obtain the office demand analysis condition;

wherein the preset demand analysis algorithm comprises a decision tree algorithm.

10. A data analysis server comprising a processing engine, a network module and a memory; the processing engine and the memory communicate through the network module, the processing engine reading a computer program from the memory and operating to perform the method of any of claims 1-9.