CN113313464A

CN113313464A - Cloud office big data processing method combined with artificial intelligence and cloud office server

Info

Publication number: CN113313464A
Application number: CN202110597725.3A
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

According to the artificial intelligence combined cloud office big data processing method and the cloud office server, the remote cooperative office information set can be analyzed and processed, so that item dividing and treating results corresponding to cloud office interaction items of the remote cooperative office information are obtained, and the item dividing and treating results are classified and treated to obtain different item dividing and treating descriptions. Can describe the analytic network of training office operation in order to ensure analytic accuracy and the reliability of the analytic network of office operation through different matters divide the branch, when carrying out redundancy office operation analysis based on the analytic network of office operation, can carry out behavioral analysis and analysis from the office operation aspect, treat to respond to office operation with accurate judgement and whether be repetitive type operation, even there is the update in operation signature or timestamp information, also can be accurate, analyze out redundancy office operation fast, avoid discerning redundancy office operation as non-redundancy office operation, avoid cloud office server repetitive execution same office operation, reduce the occupation of office service resource.

Description

Cloud office big data processing method combined with artificial intelligence and cloud office server

Technical Field

The application relates to the technical field of artificial intelligence, big data and cloud office, in particular to a cloud office big data processing method and a cloud office server combined with artificial intelligence.

Background

The remote cooperative work is mainly realized on-line work by means of the internet technology, the influence of the external work environment is small, the work arrangement is relatively flexible, the limitation of work places is avoided, and the remote cooperative work can be realized only by a computer or a mobile phone.

With the rapid development of big data technology, big data is gradually applied to various business fields, and the organic combination of big data and cloud office enables the scale of cloud office to be continuously enlarged, thereby bringing many challenges to a cloud office server.

In the research process, the inventor finds that with the continuous expansion of the cloud office scale, the data processing pressure born by the cloud office server is also continuously increased, wherein one type of data processing pressure is the response pressure to office operation. As the number of cloud office equipment is increasing, and the number of corresponding repeated operations (redundant operations) is also increasing, the cloud office server can allocate a larger part of office service resources to deal with the redundant office operations, and the operating efficiency of the cloud office server is greatly reduced. To improve this problem, it is necessary to effectively identify redundant office operations to reduce the occupation of office service resources.

Disclosure of Invention

One of the embodiments of the present application provides a cloud office big data processing method combining artificial intelligence, which is applied to a cloud office server, where a remote collaborative office information set is stored in the cloud office server in advance, and the remote collaborative office information set includes multiple groups of previous remote collaborative office information, and further, the method at least includes the following steps:

dividing and treating the prior remote cooperative office information to obtain item division and treatment results corresponding to the cloud office interaction items; the item dividing and treating result corresponding to the cloud office interaction item comprises a plurality of groups of item dividing and treating descriptions;

classifying and processing item dividing and processing results corresponding to the cloud office interaction items to obtain different item dividing and processing descriptions, and training an office operation analysis network through the different item dividing and processing descriptions; the office operation analysis network is a neural network model constructed in advance;

performing redundant office operation analysis based on the trained office operation analysis network; the office operation analysis network is used for analyzing the office operation to be responded.

Preferably, the first and second electrodes are formed of a metal,

the processing of dividing the prior remote cooperative office information to obtain item division results corresponding to the cloud office interaction items comprises the following steps:

for each group of previous remote cooperative office information in the remote cooperative office information set, performing division treatment on the cloud office interaction items of the previous remote cooperative office information according to the corresponding intelligent office environment to obtain item division treatment results corresponding to the cloud office interaction items of the previous remote cooperative office information;

classifying and processing item dividing and processing results corresponding to the cloud office interaction items to obtain different item dividing and processing descriptions, and training an office operation analysis network through the different item dividing and processing descriptions, wherein the method comprises the following steps:

determining the item division and treatment description of which the collaborative interaction accumulative times exceed the set accumulative times as the item division and treatment result corresponding to the cloud office interaction key items for each group of the plurality of groups of item division and treatment descriptions included in the item division and treatment result corresponding to the cloud office interaction items of the prior remote collaborative office information;

performing item attribute analysis processing on item division descriptions in item division results corresponding to the cloud office interaction key items, so that the item division descriptions meeting preset analysis conditions are used as focus item division descriptions representing the office cooperation degree of the remote cooperative office information set;

determining a plurality of groups of marginal item division and treatment descriptions, wherein the marginal item division and treatment descriptions are item division and treatment descriptions contained in the item division and treatment descriptions with the collaborative interaction accumulative times not exceeding the set accumulative times;

screening part of the marginal item dividing and treating descriptions as item dividing and treating descriptions to be analyzed according to feature association analysis results among the marginal item dividing and treating descriptions in a plurality of groups of marginal item dividing and treating descriptions;

training an office operation analysis network based on the focus item division description and the item division description to be analyzed of each group of previous remote cooperative office information in the remote cooperative office information set;

carrying out redundant office operation analysis based on the office operation analysis network after training, comprising:

performing office operation analysis on the received office operation to be responded based on the trained office operation analysis network to obtain an office operation analysis result; and refusing to answer the office operation to be responded when the office operation analysis result represents that the office operation to be responded is a repeated operation.

Preferably, the dividing and treating the cloud office interaction item of the previous remote cooperative office information according to the corresponding intelligent office environment to obtain an item dividing and treating result corresponding to the cloud office interaction item of the previous remote cooperative office information includes:

extracting office environment labels of a local office environment and a remote office environment from the office flow feedback information of the prior remote cooperative office information, and generating a plurality of groups of office theme interaction conditions based on the extracted office environment labels;

determining a subject treatment mode of the subject difference identification based on the interactive subject treatment conditions of the corresponding intelligent office environment according to the subject difference identification of each group of office subject interactive situations;

performing item division treatment on the cloud office interaction items of the prior remote cooperative office information according to the item division treatment mode determined by the theme difference identification corresponding to each group of office theme interaction conditions to obtain item division treatment results corresponding to the cloud office interaction items of the prior remote cooperative office information;

before determining the item classification manner of the theme difference identification based on the interactive item classification condition of the corresponding intelligent office environment according to the theme difference identification of each group of the office theme interactive situations, the method further includes preprocessing operation performed on each group of office theme interactive situations in the multiple groups of office theme interactive situations and the corresponding theme difference identification, where the preprocessing operation includes:

determining the identification optimization times of the theme difference identification of each group of office theme interaction conditions and the quantitative statistical result of the same theme difference identification of the same office theme interaction condition;

deleting the office theme interaction condition that the identifier optimization times of the theme difference identifiers exceed the set identifier optimization times and the quantitative statistical result of the same theme difference identifiers exceed the quantity threshold corresponding to the set identifier optimization times so as to obtain the reserved cloud office interaction items after deletion;

removing the theme difference interference identification corresponding to the deleted reserved cloud office interaction item, and performing identification optimization on the theme difference identification of the identification optimization directory in the deleted reserved cloud office interaction item;

and acquiring the office theme interaction condition for dividing and treating based on the deleted reserved cloud office interaction items and the theme difference identification after identification optimization.

Preferably, the determining, as the item division result corresponding to the cloud office interaction item of each set of the previous remote cooperative office information, the item division description whose cooperative interaction cumulative frequency exceeds the set cumulative frequency includes:

in item dividing and treating results corresponding to a plurality of groups of cloud office interaction items of different prior remote cooperative office information, carrying out multiple screening on item dividing and treating descriptions, and fusing the plurality of groups of item dividing and treating descriptions screened each time to obtain a plurality of groups of different item dividing and treating description sets; the multiple groups of item dividing and treating descriptions screened each time comprise item dividing and treating descriptions in item dividing and treating results corresponding to cloud office interaction items of different prior remote cooperative office information;

and screening the item division and treatment description sets with the collaborative interaction accumulated times exceeding the set accumulated times in the item division and treatment result sets formed by the multiple groups of different item division and treatment description sets to serve as item division and treatment results corresponding to the cloud office interaction key items.

Preferably, the performing item attribute analysis processing on item division and treatment descriptions in item division and treatment results corresponding to the cloud office interaction key items includes:

extracting multiple groups of item divide-and-conquer descriptions from item divide-and-conquer results corresponding to the cloud office interaction key items;

processing the extracted multi-component treatment description by at least one of the following steps:

analyzing the item attributes of the description contents in the multi-group item subdivision description to obtain item attribute analysis results aiming at the description contents;

performing item attribute analysis on the thread calling record of the operation thread corresponding to each group of item divide-and-conquer description in the multiple groups of item divide-and-conquer descriptions to obtain an item attribute analysis result aiming at the thread calling record;

adding a divide-and-conquer time sequence condition in the multi-group matter divide-and-conquer description respectively to analyze the matter attributes, and obtaining a matter attribute analysis result aiming at the divide-and-conquer time sequence;

according to the description feature correlation among the multiple groups of item division description, item attribute analysis is carried out on the multiple groups of item division description to obtain item attribute analysis results aiming at the description feature correlation;

and if the analysis credibility weight corresponding to the analysis result of the at least one type of item attribute is greater than the set credibility weight, determining the item division and treatment description corresponding to the analysis result of the at least one type of item attribute as the item division and treatment description meeting the preset analysis condition.

Preferably, the office operation resolution network comprises a plurality of resolution network elements; the training of the office operation analysis network based on the focus item division and the item division and treatment description to be analyzed of each group of previous remote cooperative office information in the remote cooperative office information set includes:

forming a network training sample by the focus item division and treatment description, the item division and treatment description to be analyzed and the project interaction information of each group of previous remote cooperative office information in the remote cooperative office information set;

training the plurality of analysis network units based on the obtained plurality of groups of network training samples;

and fusing the trained multiple analysis network units through network operation requirement information to obtain the office operation analysis network.

Preferably, before the processing, according to the corresponding intelligent office environment, of the cloud office interaction item of the previous remote cooperative office information for each group of previous remote cooperative office information in the remote cooperative office information set to obtain an item division result corresponding to the cloud office interaction item of the previous remote cooperative office information, the method further includes:

acquiring office process feedback information of a plurality of groups of initial interaction information;

according to the flow item approval record of the office flow items, carrying out flow approval analysis processing on office flow feedback information of the multiple groups of initial interactive information to obtain flow management analysis results of each group of initial interactive information, wherein the flow management analysis results are used for screening the prior remote cooperative office information from the initial interactive information;

screening part of initial interaction information to serve as prior remote cooperative office information according to the flow management analysis results of the multiple groups of initial interaction information;

wherein, the screening part of the initial interaction information as the prior remote cooperative office information according to the flow management analysis result of the plurality of groups of initial interaction information comprises at least one of the following:

screening partial initial interaction information, of which the office operation redundancy corresponding to the flow management analysis result is higher than a set redundancy threshold value, from the multiple groups of initial interaction information to serve as prior remote cooperative office information;

and according to the office operation redundancy corresponding to the flow management analysis results of the multiple groups of initial interaction information, performing descending order arrangement on the multiple groups of initial interaction information, and screening partial initial interaction information which is sorted in the front and has the quantity equal to a preset sample quantity threshold value to serve as the prior remote cooperative office information.

Preferably, the screening, in the plurality of sets of marginal event grading descriptions, a part of the marginal event grading descriptions as a to-be-analyzed item grading description according to a feature association analysis result between the marginal event grading descriptions includes:

determining the item interaction activity of the multiple groups of marginal item division description, and deleting the marginal item division description of which the item interaction activity is lower than a set activity threshold;

fusing the edge item divide-and-conquer description reserved after deletion to obtain an edge item divide-and-conquer description set;

determining a feature association analysis result between any two groups of marginal item divide-and-conquer descriptions in the marginal item divide-and-conquer description set;

determining local association analysis results of each group of marginal item divide-and-conquer description in the marginal item divide-and-conquer description set and the marginal item divide-and-conquer description set according to feature association analysis results between any two groups of marginal item divide-and-conquer descriptions; and according to the local association analysis result, sorting the marginal item division and treatment descriptions in the marginal item division and treatment description set in a descending order according to the characteristic association degree corresponding to the local association analysis result, and screening partial marginal item division and treatment descriptions which are sorted in the front to serve as item division and treatment descriptions to be analyzed.

Preferably, the office operation analysis network based on the training is used for carrying out office operation analysis on the received office operation to be responded to so as to obtain an office operation analysis result; when the office operation analysis result represents that the office operation to be responded is a repeated operation, refusing to answer the office operation to be responded, comprising the following steps:

office information distribution analysis and office information execution analysis are respectively carried out on a plurality of office operation events in the office operation to be responded, and an analysis result set aiming at office information distribution and an analysis result set aiming at office information execution are obtained;

based on a first analysis network unit of the trained office operation analysis network, performing first analysis result verification processing on the analysis result set aiming at office information distribution to obtain a first office operation analysis result comprising an office information distribution label;

based on a second analysis network unit of the trained office operation analysis network, performing second analysis result verification processing on the analysis result set executed aiming at the office information to obtain a second office operation analysis result comprising an office information execution label;

performing analysis result fusion processing based on the first office operation analysis result and the second office operation analysis result to obtain a comprehensive office operation analysis result corresponding to the office operation to be responded;

extracting a plurality of operation track characteristics from the comprehensive office operation analysis result, and clustering the operation track characteristics to obtain cluster set distribution of the operation track characteristics;

refusing to respond to the office operation to be responded when the office operation to be responded is judged to be the repeated operation according to the cluster set distribution;

wherein, said respectively performing office information distribution analysis and office information execution analysis on a plurality of office operation events in the office operation to be responded to obtain an analysis result set for office information distribution and an analysis result set for office information execution, includes:

office information distribution and analysis are respectively carried out on a plurality of office operation events in the office operation to be responded, so that office information distribution and analysis records in each office operation event and office event theme characteristics corresponding to each office information distribution and analysis record are obtained;

determining an analysis result set for office information distribution based on office information distribution analysis records and corresponding office event topic characteristics in each office operation event;

performing office information execution analysis on a plurality of office operation events in the office operation to be responded respectively to obtain an analysis result set executed aiming at the office information;

wherein, the performing office information execution analysis on the plurality of office operation events in the office operation to be responded respectively to obtain an analysis result set executed aiming at the office information includes:

respectively carrying out continuous office operation analysis on a plurality of office operation events in the office operation events to be responded to obtain continuous office operation records corresponding to the office operation events;

performing intermittent office operation analysis on a plurality of office operation events in the office operation events to be responded respectively to obtain intermittent office operation records corresponding to the office operation events respectively;

splicing the continuous office operation records and the intermittent office operation records corresponding to the same office operation event;

and performing office information execution analysis processing based on the intermittent office operation records spliced with the target continuous office operation records in the office operation events to be responded to obtain an analysis result set executed aiming at the office information.

One of the embodiments of the present application provides a cloud office 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 of an exemplary cloud office big data processing method and/or process incorporating artificial intelligence, according to some embodiments of the invention;

FIG. 2 is a block diagram of an exemplary cloud office big data processing apparatus incorporating artificial intelligence, according to some embodiments of the invention;

FIG. 3 is a block diagram of an exemplary cloud office big data processing system incorporating artificial intelligence, shown in accordance with some embodiments of the invention, an

Fig. 4 is a schematic diagram of hardware and software components in an exemplary cloud office 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 that, through research and analysis, in the related cloud office big data processing technology, a method for identifying redundant office operations is generally implemented based on operation signatures or timestamp information, but misjudgment of the existence of update operation signatures or timestamp information is easily caused, so that the redundant office operations are identified as non-redundant office operations, a server repeatedly executes the same office operations, and office service resources are greatly occupied.

In order to solve the problems, the inventor provides a cloud office big data processing method and a cloud office server in combination with artificial intelligence, and can analyze and process a pre-recorded remote cooperative office information set so as to obtain a matter division result corresponding to a cloud office interaction matter of the remote cooperative office information, and thus, the classification processing of the matter division result can be further realized to obtain different matter division descriptions. So, can describe the analytic network of training office operation through different matters divide and conquer, in order to ensure analytic accuracy and the reliability of the analytic network of office operation, when carrying out redundancy office operation analysis based on the analytic network of office operation that the training was accomplished, can operate analysis and discernment from the office operation aspect like this, even there is the update in operation signature or timestamp information, also can be accurate, analyze out redundancy office operation fast, avoid discerning redundancy office operation for non-redundancy office operation, can avoid cloud office server to carry out same office operation repeatedly like this, reduce the occupation of office service resource as far as possible.

First, an exemplary cloud office big data processing method with artificial intelligence is described, referring to fig. 1, which is a flowchart of an exemplary cloud office big data processing method and/or process with artificial intelligence according to some embodiments of the present invention, and a cloud office big data processing method with artificial intelligence may include the following technical solutions described in steps S1-S3.

It can be understood that, in this embodiment, the cloud office server stores a remote collaborative office information set in advance, the remote collaborative office information set includes a plurality of sets of previous remote collaborative office information, and the cloud office server may be a Mysql data server or a Hive data server, or another type of data server, which is not limited herein. In this scheme, the remote cooperative office information set may record different previous remote cooperative office information according to a chronological order, and the previous remote cooperative office information may be interactive data between different online office devices or between an online office device and a cloud office server, for example, the remote cooperative office information set may be as follows:

{

message1, online office equipment 1, online office equipment 2, time1, information description X;

message2, online office equipment 3, online office equipment 6, time2, information description X;

message3, cloud office server, online office equipment 2, time3, information description X;

message4, online office equipment 1, cloud office server, time4, information description X;

message5, online office equipment 6, cloud office server, time5, information description X;

message6, cloud office server, online office equipment 3, time6, information description X;

}

on the basis of the above, the method may include the following.

And step S1, performing division treatment on the prior remote cooperative office information to obtain a matter division treatment result corresponding to the cloud office interaction matter. For example, cloud office interaction events can be data corresponding to operations performed by different offices (online office equipment or cloud office servers) for teleworking, including but not limited to office performance assessment, office project guidance, project node assignment, project processing schedules, project file sharing, and the like. Further, the item division and treatment result corresponding to the cloud office interaction item includes multiple sets of item division and treatment descriptions, each set of item division and treatment description may be regarded as a complete operation behavior, for example, the item division and treatment description M1 may be understood as a file downloading operation behavior, the item division and treatment description M2 may be understood as a video conference initiating operation behavior, and the item division and treatment description M3 may be understood as an office software updating operation behavior. By the design, the prior remote cooperative office information can be accurately split, so that the follow-up credible coefficient based on office operation analysis is ensured, and analytic errors are avoided.

In a further embodiment, the dividing and treating the prior remote cooperative office information to obtain an item dividing and treating result corresponding to the cloud office interaction item includes: for each group of previous teleworking cooperative office information in the teleworking cooperative office information set, the cloud office interaction items of the previous teleworking cooperative office information are subjected to division treatment according to the corresponding intelligent office environment, so that an item division treatment result corresponding to the cloud office interaction items of the previous teleworking cooperative office information is obtained. For example, intelligent office environments may be differentiated in different ways. Due to the design, the item division of the cloud office interaction items can be realized as finely as possible, so that a basis which is as perfect as possible is provided for subsequent office operation and data analysis.

Further, the dividing and treating the cloud office interaction item of the previous remote cooperative office information according to the corresponding intelligent office environment to obtain an item dividing and treating result corresponding to the cloud office interaction item of the previous remote cooperative office information may include the following contents: extracting office environment labels of a local office environment and a remote office environment from the office flow feedback information of the prior remote cooperative office information, and generating a plurality of groups of office theme interaction conditions based on the extracted office environment labels; determining a subject treatment mode of the subject difference identification based on the interactive subject treatment conditions of the corresponding intelligent office environment according to the subject difference identification of each group of office subject interactive situations; and performing item division treatment on the cloud office interaction items of the prior remote cooperative office information according to the item division treatment mode determined by the theme difference identification corresponding to each group of office theme interaction conditions so as to obtain item division treatment results corresponding to the cloud office interaction items of the prior remote cooperative office information. In this embodiment, the office flow feedback information may be used to record different office flow events, such as office event operation nodes, office event operation schedules, and the like. The office environment labels can distinguish intelligent office environments with different scales, the office theme interaction condition is used for representing the interaction condition between different office ends, and the item division and treatment mode can comprise different item division and treatment indication information, such as according to what mode or what standard to perform data screening.

It can be understood that the basic idea of divide and conquer processing (divide and conquer algorithm) is to decompose a problem of size N into K sub-problems of smaller size, which are independent of each other and of the same nature as the original problem. The solution of the original problem can be obtained by solving the solution of the subproblem. By the aid of the algorithm, the efficiency of redundant operation behavior identification can be improved.

In some embodiments, before determining the item classification manner of the theme difference identifier based on the interaction item classification condition of the corresponding intelligent office environment according to the theme difference identifier of each group of the office theme interaction situations, the method further includes a preprocessing operation performed on each group of the office theme interaction situations in the plurality of groups of office theme interaction situations and the corresponding theme difference identifier. On the basis, the preprocessing operation comprises the following steps: determining the identification optimization times of the theme difference identification of each group of office theme interaction conditions and the quantitative statistical result of the same theme difference identification of the same office theme interaction condition; deleting the office theme interaction condition that the identifier optimization times of the theme difference identifiers exceed the set identifier optimization times and the quantitative statistical result of the same theme difference identifiers exceed the quantity threshold corresponding to the set identifier optimization times so as to obtain the reserved cloud office interaction items after deletion; removing the theme difference interference identification corresponding to the deleted reserved cloud office interaction item, and performing identification optimization on the theme difference identification of the identification optimization directory in the deleted reserved cloud office interaction item; and acquiring the office theme interaction condition for dividing and treating based on the deleted reserved cloud office interaction items and the theme difference identification after identification optimization. By the design, the timeliness of the interaction condition of the office subject and the corresponding subject difference identification can be ensured by preprocessing, so that accurate and reliable training samples are provided for subsequent model training.

In some other embodiments, before the performing, for each group of previous remote cooperative office information in the remote cooperative office information set, a treatment on the cloud office interaction item of the previous remote cooperative office information according to the corresponding intelligent office environment to obtain an item treatment result corresponding to the cloud office interaction item of the previous remote cooperative office information, the method may further include the following steps: acquiring office process feedback information of a plurality of groups of initial interaction information; according to the flow item approval record of the office flow items, carrying out flow approval analysis processing on office flow feedback information of the multiple groups of initial interactive information to obtain flow management analysis results of each group of initial interactive information, wherein the flow management analysis results are used for screening the prior remote cooperative office information from the initial interactive information; and screening part of the initial interactive information as the prior remote cooperative office information according to the flow management analysis result of the plurality of groups of initial interactive information. By the design, the process management analysis result can be considered when the prior remote cooperative office information is determined, so that the completeness of process approval can be considered when the model obtained by subsequent training is analyzed in office operation.

In this embodiment, the screening part of the initial interaction information as the previous remote cooperative office information according to the flow management analysis result of the plurality of sets of initial interaction information includes at least one of the following embodiments.

In the embodiment (1), the initial interaction information of the plurality of sets, in which the office operation redundancy corresponding to the flow management analysis result is higher than the set redundancy threshold, is selected as the previous remote cooperative office information.

In the implementation mode (2), according to the office operation redundancy corresponding to the process management analysis results of the multiple sets of initial interactive information, the multiple sets of initial interactive information are sorted in a descending order, and partial initial interactive information which is sorted in the front and is in the number of the preset sample number threshold is screened to be used as the prior remote cooperative office information.

And step S2, classifying and processing item dividing and treating results corresponding to the cloud office interaction items to obtain different item dividing and treating descriptions, and training an office operation analysis network according to the different item dividing and treating descriptions. For example, the different item division and treatment descriptions may include a focus item division and treatment description, an edge item division and treatment description, and/or an item division and treatment description to be analyzed, the focus item division and treatment description corresponds to an office operation with a relatively high attention, the edge item division and treatment description corresponds to an office operation with a relatively low attention, and the office operation analysis Network may be a neural Network model (VGG).

In a further embodiment, in order to ensure the parsing accuracy and generalization ability of the office operation parsing network after training, the different event division descriptions need to be classified accurately, and for this purpose, the content described in step S2 can be realized through the following steps S21-S25.

Step S21, for a plurality of sets of item division and treatment descriptions included in the item division and treatment result corresponding to the cloud office interaction item of each set of the previous remote cooperative office information, determining the item division and treatment description whose cooperative interaction cumulative frequency exceeds a set cumulative frequency as the item division and treatment result corresponding to the cloud office interaction key item. In this embodiment, the collaborative interaction accumulated times can be used for representing the times of the shared use of the cloud office server and the online office equipment by the item division and management description, and the more the shared use times, the more important the cloud office interaction items corresponding to the item division and management description is, so that the cloud office interaction key items can also be understood as the cloud office interaction items focused by the cloud office server. Further, this step may include the following: in item dividing and treating results corresponding to a plurality of groups of cloud office interaction items of different prior remote cooperative office information, carrying out multiple screening on item dividing and treating descriptions, and fusing the plurality of groups of item dividing and treating descriptions screened each time to obtain a plurality of groups of different item dividing and treating description sets; the multiple groups of item dividing and treating descriptions screened each time comprise item dividing and treating descriptions in item dividing and treating results corresponding to cloud office interaction items of different prior remote cooperative office information; and screening the item division and treatment description sets with the collaborative interaction accumulated times exceeding the set accumulated times in the item division and treatment result sets formed by the multiple groups of different item division and treatment description sets to serve as item division and treatment results corresponding to the cloud office interaction key items. It is understood that the set cumulative number may be adjusted according to the size of the office item.

Step S22, performing item attribute analysis processing on item division descriptions in the item division result corresponding to the cloud office interaction key item, so as to use the item division description meeting a preset analysis condition as a focus item division description representing the office collaboration degree of the remote collaborative office information set. In this embodiment, the item attribute may be used to distinguish different item division descriptions, and the item attribute may be a form attribute or a concept attribute, which is not limited herein. The office cooperation degree of the remote cooperative office information set is used for representing the cooperative compatibility of the remote cooperative office information set, and the higher the office cooperation degree is, the stronger the cooperative compatibility of the remote cooperative office information set is. Further, the performing item attribute analysis processing on the item division description in the item division result corresponding to the cloud office interaction key item may include: and extracting multiple groups of item divide-and-conquer descriptions from item divide-and-conquer results corresponding to the cloud office interaction key items. Based on this, whether the item divide and conquer description satisfies the preset parsing condition can be realized as follows.

First, the extracted multi-component treatment description is subjected to at least one of the following treatments:

(1) analyzing the item attributes of the description contents in the multi-group item subdivision description to obtain item attribute analysis results aiming at the description contents;

(2) performing item attribute analysis on the thread calling record of the operation thread corresponding to each group of item divide-and-conquer description in the multiple groups of item divide-and-conquer descriptions to obtain an item attribute analysis result aiming at the thread calling record;

(3) adding a divide-and-conquer time sequence condition in the multi-group matter divide-and-conquer description respectively to analyze the matter attributes, and obtaining a matter attribute analysis result aiming at the divide-and-conquer time sequence;

(4) and analyzing the item attributes of the multi-group item division and treatment description according to the description feature correlation among the multi-group item division and treatment description to obtain an item attribute analysis result aiming at the description feature correlation.

Secondly, if the analysis credibility weight corresponding to the analysis result of the at least one type of item attribute is larger than the set credibility weight, determining the item division and treatment description corresponding to the analysis result of the at least one type of item attribute as the item division and treatment description meeting the preset analysis condition. In the scheme, the analytic credibility weight can be understood as an analytic credibility coefficient, and the numerical range of the analytic credibility weight can be 0-1.

By the design, whether the corresponding item division and treatment description meets the preset analysis condition can be judged based on the analysis credible weight of the item attribute analysis results of different layers, so that omission of the item division and treatment description of the focus can be avoided.

Step S23, determining a plurality of sets of edge item division and treatment descriptions, where the edge item division and treatment descriptions are item division and treatment descriptions included in the item division and treatment descriptions whose collaborative interaction cumulative frequency does not exceed the set cumulative frequency.

Step S24, in the multiple sets of marginal item division and treatment descriptions, according to the feature association analysis result between the marginal item division and treatment descriptions, screening partial marginal item division and treatment descriptions as item division and treatment descriptions to be analyzed. For example, the feature association analysis result may be similarity of operation behaviors between different edge event subtotal descriptions, and the event subtotal description to be analyzed may be understood as an edge event subtotal description which may be a focus event subtotal description, that is, an event subtotal description located between the focus event subtotal description and the edge event subtotal description. Further, this step may include the following: determining the item interaction activity of the multiple groups of marginal item division description, and deleting the marginal item division description of which the item interaction activity is lower than a set activity threshold; fusing the edge item divide-and-conquer description reserved after deletion to obtain an edge item divide-and-conquer description set; determining a feature association analysis result between any two groups of marginal item divide-and-conquer descriptions in the marginal item divide-and-conquer description set; determining local association analysis results of each group of marginal item divide-and-conquer description in the marginal item divide-and-conquer description set and the marginal item divide-and-conquer description set according to feature association analysis results between any two groups of marginal item divide-and-conquer descriptions; and according to the local association analysis result, sorting the marginal item division and treatment descriptions in the marginal item division and treatment description set in a descending order according to the characteristic association degree corresponding to the local association analysis result, and screening partial marginal item division and treatment descriptions which are sorted in the front to serve as item division and treatment descriptions to be analyzed.

Step S25, training an office operation analysis network based on the focus item division description and the item division description to be analyzed of each group of previous remote cooperative office information in the remote cooperative office information set. In this embodiment, the office operation analysis network includes a plurality of analysis network units, and further, the manner of training the office operation analysis network may include what is described in the following steps: forming a network training sample by the focus item division and treatment description, the item division and treatment description to be analyzed and the project interaction information of each group of previous remote cooperative office information in the remote cooperative office information set; training the plurality of analysis network units based on the obtained plurality of groups of network training samples; and fusing the trained multiple analysis network units through network operation requirement information to obtain the office operation analysis network.

And step S3, performing redundant office operation analysis based on the trained office operation analysis network. In the present embodiment, the redundant office operation parsing may be a related measure performed for the parsing result of the office operation, such as responding to the office operation or intercepting (rejecting an answer) the office operation. Further, this step may include the following: performing office operation analysis on the received office operation to be responded based on the trained office operation analysis network to obtain an office operation analysis result; and refusing to answer the office operation to be responded when the office operation analysis result represents that the office operation to be responded is a repeated operation. In this embodiment, the office operation to be responded may be initiated by any online office device in communication with the cloud office server.

On the basis of step S3, in order to achieve accurate resolution of the office operation to be responded to, it can be achieved by the following steps S31-S36.

Step S31, performing office information distribution analysis and office information execution analysis on the plurality of office operation events in the office operation to be responded, respectively, to obtain an analysis result set for office information distribution and an analysis result set for office information execution. Further, the performing office information distribution analysis and office information execution analysis on the plurality of office operation events in the office operation to be responded respectively to obtain an analysis result set for office information distribution and an analysis result set for office information execution, includes: office information distribution and analysis are respectively carried out on a plurality of office operation events in the office operation to be responded, so that office information distribution and analysis records in each office operation event and office event theme characteristics corresponding to each office information distribution and analysis record are obtained; determining an analysis result set for office information distribution based on office information distribution analysis records and corresponding office event topic characteristics in each office operation event; and respectively carrying out office information execution analysis on the plurality of office operation events in the office operation to be responded to obtain an analysis result set executed aiming at the office information.

On the basis of the step S31, the performing office information analysis on each of the plurality of office operation events in the office operation to be responded to obtain an analysis result set performed on the office information includes: respectively carrying out continuous office operation analysis on a plurality of office operation events in the office operation events to be responded to obtain continuous office operation records corresponding to the office operation events; performing intermittent office operation analysis on a plurality of office operation events in the office operation events to be responded respectively to obtain intermittent office operation records corresponding to the office operation events respectively; splicing the continuous office operation records and the intermittent office operation records corresponding to the same office operation event; and performing office information execution analysis processing based on the intermittent office operation records spliced with the target continuous office operation records in the office operation events to be responded to obtain an analysis result set executed aiming at the office information.

It is understood that, through the content described in step S31, it is possible to perform differential parsing based on office information distribution and office information execution, and perform analysis and concatenation of the continuous office operation records and the intermittent office operation records for office information execution, so that the parsing result set of office information distribution and the parsing result set performed for office information can be completely determined.

And step S32, based on the trained first analysis network unit of the office operation analysis network, performing first analysis result verification processing on the analysis result set aiming at office information distribution to obtain a first office operation analysis result comprising an office information distribution label. In an alternative embodiment, the performing, by the first analysis network unit of the trained office operation analysis network, a first analysis result verification process on the analysis result set assigned to the office information to obtain a first office operation analysis result including an office information assignment tag may include: performing event label matching on each office operation event in the analysis result set distributed aiming at the office information respectively to obtain a nonrepeating operation event label corresponding to each office operation event; respectively carrying out analysis record time sequence correction processing on the basis of an operation characteristic detection result of an office information distribution analysis record corresponding to a corresponding unrepeated operation event label in each office operation event to obtain a corrected analysis result set for office information distribution; performing secondary time sequence correction processing on the corrected analysis result set for office information distribution to obtain a plurality of first candidate office operation analysis results including office information distribution labels; and according to the office information distribution types respectively matched with the first candidate office operation analysis results, performing office operation analysis result fusion on the first candidate office operation analysis results belonging to the same office information distribution type to obtain a first office operation analysis result comprising an office information distribution label. Therefore, the office operation analysis results can be fused based on the time sequence level and the office information distribution type, and the global relevance and accuracy of the first office operation analysis results including the office information distribution labels can be ensured.

In an alternative embodiment, the performing event label matching on each office operation event in the analysis result set allocated for the office information respectively to obtain a nonrepetitive operation event label corresponding to each office operation event includes: for each office operation event in the analysis result set distributed aiming at the office information, when the number of the office event topic characteristics of the office operation event is more than one, acquiring an event label access index of each office event topic characteristic; when the office event subject characteristics with the highest event label access index are one, determining unrepeated operation event labels of corresponding office operation events based on the office event subject characteristics with the highest event label access index; when the number of the office event topic characteristics with the highest event label access index is more than one, acquiring an analysis record access index of a corresponding office information distribution analysis record aiming at the office event topic characteristics with the highest event label access index; and determining a nonrepetitive operation event label corresponding to the corresponding office operation event according to the office event theme characteristics corresponding to the highest analysis record access index. By the design, the nonrepeating operation event label corresponding to the corresponding office operation event can be accurately determined based on the analysis record access index.

In an alternative embodiment, the performing analysis record timing correction processing based on the operation feature detection result of the office information distribution analysis record corresponding to the non-repetitive operation event label in each office operation event respectively to obtain a corrected analysis result set for office information distribution includes: for each office operation event, acquiring a behavior analysis error quantization value of an office information distribution analysis record corresponding to a corresponding nonrepeating operation event label in each office operation event; when the behavior analysis error quantized value is within a preset error quantized value numerical range, marking a corresponding office information distribution analysis result, wherein the marked office information distribution analysis result comprises office information distribution analysis records and nonrepetitive operation event labels corresponding to the office information distribution analysis records; when the behavior analysis error quantized value is not in the numerical range of the preset error quantized value, determining an office information distribution analysis result of the corresponding office operation event as an invalid result; and distributing analysis results based on the office information corresponding to each office operation event to obtain a corrected analysis result set for office information distribution. By the design, the behavior analysis error quantization value can be taken into account, so that accurate and reliable correction of an analysis result set distributed aiming at office information is realized.

And step S33, based on the second analysis network unit of the trained office operation analysis network, performing second analysis result verification processing on the analysis result set executed aiming at the office information to obtain a second office operation analysis result comprising an office information execution label. It is understood that the implementation of this step is similar to the implementation of step S32, and therefore will not be further described here.

And step S34, carrying out analysis result fusion processing based on the first office operation analysis result and the second office operation analysis result to obtain a comprehensive office operation analysis result corresponding to the office operation to be responded. In the scheme, the comprehensive office operation analysis result can realize the evaluation of the office operation to be responded from the office information distribution level and the office information execution level.

And step S35, extracting a plurality of operation track characteristics from the comprehensive office operation analysis result, and clustering the operation track characteristics to obtain a cluster set distribution of the operation track characteristics. For example, the operation trajectory feature may include an operation time feature, a process approval feature, an operation event feature, and the like, which are not limited herein.

And step S36, refusing to answer the office operation to be responded when the office operation to be responded is judged to be the repeated operation according to the cluster set distribution. In this embodiment, whether the office operation to be responded is the repetitive operation may be determined according to the global operation probability corresponding to each type of result in the cluster set distribution, for example, if the average value of the global operation probabilities corresponding to each type of result exceeds the set repeatability evaluation probability, it may be determined that the office operation to be responded is the repetitive operation. The global operation probability corresponding to each type of result can be obtained by calculating according to the index weights corresponding to different operation track characteristics, and related calculation formulas and codes are not described herein again.

It can be understood that by implementing the above steps S31-S36, the office operation analysis results of the office operation to be responded on different levels can be determined based on the trained office operation analysis network, so that a plurality of operation trajectory features are extracted from the obtained comprehensive office operation analysis results, and thus whether the office operation to be responded is a repetitive operation can be accurately determined based on the repeatability evaluation probability corresponding to the cluster set distribution of the operation trajectory features, and the behavior analysis and analysis can be performed from the office operation level.

In summary, based on the above steps S1-S3, the pre-recorded remote cooperative office information set can be analyzed and processed, so as to obtain the item division and treatment result corresponding to the cloud office interaction item of the remote cooperative office information, and thus, the classification processing of the item division and treatment result can be further realized to obtain different item division and treatment descriptions. So, can describe the analytic network of training office operation through different matters divide and conquer, in order to ensure analytic accuracy and the reliability of the analytic network of office operation, when carrying out redundancy office operation analysis based on the analytic network of office operation that the training was accomplished, can carry out behavioral analysis and analysis from the office operation aspect, whether to be the repetitive operation with the response office operation with accurate judgement, even there is the update in operation signature or timestamp information, also can be accurate, analyze out redundancy office operation fast, avoid discerning redundancy office operation as non-redundancy office operation, can avoid cloud office server to carry out same office operation repeatedly like this, reduce the occupation of office service resource as far as possible.

For some possible embodiments, after redundant office operation analysis is performed based on the trained office operation analysis network, the terminal identifier of the online office equipment corresponding to the office operation to be responded, which is determined to be the repetitive operation, may be stored, so that subsequent targeted risk investigation may be performed on the online office equipment.

Next, for the above cloud office big data processing method combining artificial intelligence, an exemplary cloud office big data processing apparatus combining artificial intelligence is further provided in the embodiment of the present invention, as shown in fig. 2, a cloud office big data processing apparatus 200 combining artificial intelligence may include the following functional modules.

The item dividing and treating module 210 is configured to divide and treat the previous remote cooperative office information to obtain an item dividing and treating result corresponding to the cloud office interaction item; the item dividing and treating result corresponding to the cloud office interaction item comprises a plurality of groups of item dividing and treating descriptions.

The result classifying module 220 is used for classifying and processing the item dividing and treating result corresponding to the cloud office interaction item to obtain different item dividing and treating descriptions, and training an office operation analysis network according to the different item dividing and treating descriptions; the office operation analysis network is a neural network model constructed in advance.

An office analysis module 230, configured to perform redundant office operation analysis based on the trained office operation analysis network; the office operation analysis network is used for analyzing the office operation to be responded.

It is understood that the description of the functional modules above may refer to the description of the method shown in fig. 1 and will therefore not be described further herein.

Then, based on the above method embodiment and apparatus embodiment, the embodiment of the present invention further provides a system embodiment, that is, a cloud office big data processing system combined with artificial intelligence, please refer to fig. 3, and a cloud office big data processing system 30 combined with artificial intelligence may include a cloud office server 10 and an online office device 20. Wherein the cloud office server 10 and the online office device 20 are in communication to implement the above method, further, the functionality of a cloud office big data processing system 30 in combination with artificial intelligence is described as follows.

A cloud office big data processing system combined with artificial intelligence comprises a cloud office server and online office equipment which are in communication connection with each other, wherein a remote cooperative office information set is stored in the cloud office server in advance, and the remote cooperative office information set comprises a plurality of groups of previous remote cooperative office information;

further, the cloud office server is configured to: dividing and treating the prior remote cooperative office information to obtain item division and treatment results corresponding to the cloud office interaction items; the item dividing and treating result corresponding to the cloud office interaction item comprises a plurality of groups of item dividing and treating descriptions; classifying and processing item dividing and processing results corresponding to the cloud office interaction items to obtain different item dividing and processing descriptions, and training an office operation analysis network through the different item dividing and processing descriptions; the office operation analysis network is a neural network model constructed in advance; performing redundant office operation analysis based on the trained office operation analysis network; the office operation analysis network is used for analyzing the office operation to be responded.

It will be appreciated that the above description of the system embodiment may refer to the description of the method embodiment shown in fig. 1 and will therefore not be described further herein.

Further, referring to fig. 4 in combination, the cloud office server 10 may include a processing engine 110, a network module 120, and a memory 130, wherein the processing engine 110 and the memory 130 communicate 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 is to be understood that the configuration shown in fig. 4 is merely illustrative, and that the cloud office server 10 may include more or fewer components than shown in fig. 2, or 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 cloud office big data processing method combined with artificial intelligence is characterized by being applied to a cloud office server, wherein a remote cooperative office information set is stored in the cloud office server in advance, and the remote cooperative office information set comprises multiple groups of previous remote cooperative office information, and further comprising at least the following steps:

2. The method of claim 1,

3. The method according to claim 2, wherein the dividing and treating the cloud office interaction item of the previous remote cooperative office information according to the corresponding intelligent office environment to obtain an item dividing and treating result corresponding to the cloud office interaction item of the previous remote cooperative office information comprises:

4. The method according to claim 2, wherein the determining, for the plurality of sets of item division and treatment descriptions included in the item division and treatment results corresponding to the cloud office interaction items of each set of the previous remote cooperative office information, the item division and treatment description whose cooperative interaction cumulative frequency exceeds the set cumulative frequency as the item division and treatment result corresponding to the cloud office interaction key item includes:

5. The method according to claim 2, wherein the performing item attribute analysis processing on item division description in item division results corresponding to the cloud office interaction key items comprises:

6. The method of claim 2, wherein the office operations resolution network comprises a plurality of resolution network elements; the training of the office operation analysis network based on the focus item division and the item division and treatment description to be analyzed of each group of previous remote cooperative office information in the remote cooperative office information set includes:

7. The method according to any one of claims 2 to 6, wherein before the, for each group of previous teleworking cooperative office information in the set of teleworking office information, performing a treatment on the cloud office interaction item of the previous teleworking office information according to the corresponding intelligent office environment to obtain an item treatment result corresponding to the cloud office interaction item of the previous teleworking office information, the method further comprises:

8. The method according to any one of claims 2 to 6, wherein the screening, in the plurality of sets of marginal event grading descriptions, a part of the marginal event grading descriptions as a subject event grading description to be analyzed according to a feature association analysis result between the marginal event grading descriptions comprises:

9. The method according to claim 2, wherein the received office operation to be responded is analyzed based on the trained office operation analysis network to obtain an office operation analysis result; when the office operation analysis result represents that the office operation to be responded is a repeated operation, refusing to answer the office operation to be responded, comprising the following steps:

10. The cloud office server is characterized by 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.