CN114186607A

CN114186607A - Big data processing method and artificial intelligence server applied to cloud office

Info

Publication number: CN114186607A
Application number: CN202111292090.2A
Authority: CN
Inventors: 张俊杰
Original assignee: Individual
Current assignee: Individual
Priority date: 2021-11-03
Filing date: 2021-11-03
Publication date: 2022-03-15

Abstract

According to the big data processing method and the artificial intelligence server applied to cloud office, cloud office big data to be processed are analyzed and recognized through the cloud office big data recognition thread, so that a first significant office interaction behavior set, interaction elements of each office interaction data fragment in first hot spot office interaction data and intention demand interaction elements of each office event in the first hot spot office interaction data are obtained, and a collaborative office recognition result is determined. Therefore, compared with a mode of directly performing cooperative office identification on the interactive element distribution of the first hot spot office interactive data in the related art, the scheme can be used for landing on the interactive elements of the office interactive data fragments and the intention demand interactive elements of office events, so that the accuracy of the cooperative office identification result is ensured, the cooperative office identification result is ensured to be matched with the actual office business scene and office business demand as far as possible, and a basis for making a decision credible is provided for the subsequent update and upgrade of office service software.

Description

Big data processing method and artificial intelligence server applied to cloud office

Technical Field

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

Background

The big data opens a new era for people. The revolution caused by the big data is in a square surface and can concern public health, the business field, the traditional thinking and the like, the big data opens a great era transformation, and the industry revolution process of the world is continuously promoted.

Under a big data environment, online office (also called as teleworking or cloud office) is one of a plurality of emerging business modes, and can break through the regional limitation and the time limitation of the traditional office, so that the waste of office resources is reduced.

To meet the increasing office demand and cope with the complex network office environment, big data based online office technology needs to be constantly optimized and updated to minimize the negative impact in this office model. For optimization and update of the online office technology, an important link is to analyze and identify office data, so that targeted optimization and update of the online office technology are performed according to relevant results obtained by analysis and identification. However, the related analysis and identification technology for office data still needs further improvement.

Disclosure of Invention

In view of the foregoing, the present application provides the following.

The scheme of one embodiment of the application provides a cloud office big data identification method, which is applied to an artificial intelligence server, and comprises the following steps:

calling a cloud office big data identification thread to obtain a first remarkable office interaction behavior set in cloud office big data to be processed, and determining first hot spot office interaction data in the cloud office big data to be processed and interaction element distribution of the first hot spot office interaction data;

calling the cloud office big data identification thread to split the first hot spot office interactive data into a plurality of office interactive data fragments, extracting interactive elements corresponding to each office interactive data fragment in the first hot spot office interactive data by combining with the interactive element distribution of the first hot spot office interactive data, and acquiring intention demand interactive elements of each office event in the first hot spot office interactive data;

and acquiring a cooperative office identification result based on the interaction element of each office interaction data fragment in the first hot spot office interaction data, the information of the first significant office interaction behavior set and the intention demand interaction element of each office event in the first hot spot office interaction data.

Preferably, the calling the cloud office big data identification thread to obtain a first significant office interaction behavior set in the cloud office big data to be processed, and determining the first hot spot office interaction data in the cloud office big data to be processed and the interaction element distribution of the first hot spot office interaction data, includes:

importing cloud office big data to be processed into a cloud office big data identification thread;

calling the cloud office big data identification thread to obtain a first significant office interaction behavior set in the cloud office big data to be processed;

calling the cloud office big data identification thread to acquire first hot spot office interaction data and interaction element distribution of the first hot spot office interaction data in the cloud office big data to be processed based on the first remarkable office interaction behavior set, wherein the first hot spot office interaction data is office interaction data corresponding to the first remarkable office interaction behavior set in the cloud office big data to be processed;

the calling of the cloud office big data identification thread splits the first hot spot office interactive data into a plurality of office interactive data fragments, extracts an interactive element corresponding to each office interactive data fragment in the first hot spot office interactive data by combining with the interactive element distribution of the first hot spot office interactive data, and obtains an intention demand interactive element of each office event in the first hot spot office interactive data, including:

calling the cloud office big data identification thread to split the first hot spot office interactive data into a plurality of office interactive data fragments, calling the cloud office big data identification thread to extract an interactive element corresponding to each office interactive data fragment in the first hot spot office interactive data based on the interactive element distribution of the first hot spot office interactive data, and calling the cloud office big data identification thread to acquire an intention demand interactive element of each office event in the first hot spot office interactive data, wherein the interactive element corresponding to the office interactive data fragment is a detection result of significant office interactive behavior in the office interactive data fragment.

Preferably, the information of the first significant office interaction behavior set includes a type of the first significant office interaction behavior set, and the obtaining of the collaborative office identification result based on the interaction element of each office interaction data segment in the first hot spot office interaction data, the information of the first significant office interaction behavior set, and the intention requirement interaction element of each office event in the first hot spot office interaction data includes:

determining office interaction data with the significant office interaction behavior in the first hotspot office interaction data based on interaction elements corresponding to each office interaction data segment in the first hotspot office interaction data, and determining the type of the office event in the first hotspot office interaction data based on intention demand interaction elements of each office event in the first hotspot office interaction data, wherein the interaction elements corresponding to the office interaction data segments corresponding to the office interaction data with the significant office interaction behavior are larger than a preset detection result threshold;

and determining the office events belonging to the type of the first significant office interaction behavior set in the office interaction data with significant office interaction behaviors as the cooperative office identification result based on the type of each office event in the first hot spot office interaction data.

Preferably, the calling the cloud office big data identification thread to obtain a first significant office interaction behavior set in the cloud office big data to be processed includes:

calling the cloud office big data identification thread to obtain first original interaction element distribution in the cloud office big data to be processed;

and calling the cloud office big data identification thread to obtain a first remarkable office interaction behavior set in the cloud office big data to be processed based on the first original interaction element distribution.

Preferably, the information of the first significant office interaction behavior set includes a correlation condition of the first significant office interaction behavior set, and the invoking of the cloud office big data identification thread to obtain an intention demand interaction element of each office event in the first hotspot office interaction data includes:

calling the cloud office big data identification thread to identify intention requirements of the first original interaction element distribution to obtain interaction element distribution corresponding to first intention requirement identification information corresponding to each office event in the cloud office big data to be processed;

determining, based on the association condition of the first significant office interaction behavior set, an interaction element corresponding to each office event in the first hot spot office interaction data in the interaction element distribution corresponding to the first intention demand identification information, as an intention demand interaction element corresponding to the office event in the first hot spot office interaction data.

Preferably, the invoking the cloud office big data identification thread to obtain a first significant office interaction behavior set in the to-be-processed cloud office big data based on the first original interaction element distribution includes:

calling the cloud office big data identification thread to obtain a first significant alternative interaction behavior set in the cloud office big data to be processed based on the first original interaction element distribution;

calling the cloud office big data identification thread to obtain the interaction element distribution of second hot spot office interaction data in the cloud office big data to be processed based on the first significant alternative interaction behavior set and the first original interaction element distribution;

and calling the cloud office big data identification thread to acquire the first remarkable office interaction behavior set based on the interaction element distribution of the second hot spot office interaction data.

Preferably, the invoking the cloud office big data recognition thread acquires the first significant office interaction behavior set based on the interaction element distribution of the second hot spot office interaction data, and the method includes:

calling the cloud office big data identification thread to acquire detection interaction element distribution and error interaction element distribution corresponding to interaction element distribution of the second hot spot office interaction data; the detection interaction element distribution is used for representing that the first significant alternative interaction behavior set belongs to detection results of various types, and the error interaction element distribution is used for representing the deviation of the first significant office interaction behavior set relative to the first significant alternative interaction behavior set;

acquiring information of the first significant office interaction behavior set based on detection interaction element distribution corresponding to the interaction element distribution of the second hot spot office interaction data and error interaction element distribution corresponding to the interaction element distribution of the second hot spot office interaction data;

the information of the first significant office interaction behavior set further includes a correlation condition of the first significant office interaction behavior set and a type of the first significant office interaction behavior set, and the information of the first significant office interaction behavior set is obtained based on a detection interaction element distribution corresponding to an interaction element distribution of the second hot spot office interaction data and an error interaction element distribution corresponding to an interaction element distribution of the second hot spot office interaction data, and includes:

performing threshold screening on detection interactive element distribution corresponding to the interactive element distribution of the second hot spot office interactive data to obtain the type of the first significant office interactive behavior set;

and performing deviation correction on the association condition of the error interaction element distribution corresponding to the interaction element distribution of the second hotspot office interaction data and the first remarkable alternative interaction behavior set to obtain the association condition of the first remarkable office interaction behavior set.

Preferably, before the step of calling the cloud office big data identification thread to acquire the first significant office interaction behavior set in the to-be-processed cloud office big data, the method further includes: configuring the cloud office big data identification thread;

the configuring the cloud office big data identification thread comprises the following steps:

importing sample cloud office big data into the cloud office big data identification thread; calling the cloud office big data identification thread to obtain second original interaction element distribution of the sample cloud office big data;

calling the cloud office big data identification thread to obtain the interaction element distribution of second hot spot office interaction data and third hot spot office interaction data in the sample cloud office big data based on the second original interaction element distribution;

calling the cloud office big data identification thread to divide the second hot spot office interaction data into a plurality of office interaction data fragments, calling the cloud office big data identification thread to extract interaction elements corresponding to each office interaction data fragment in the second hot spot office interaction data based on the interaction element distribution of the third hot spot office interaction data, and calling the cloud office big data identification thread to perform intention demand identification on the second original interaction element distribution so as to obtain interaction element distribution corresponding to second intention demand identification information;

acquiring a first thread operation index of the cloud office big data identification thread based on a comparison result between an interaction element corresponding to each office interaction data segment in the second hot spot office interaction data and a first real element, and acquiring a second thread operation index of the cloud office big data identification thread based on a comparison result between interaction element distribution corresponding to the second intention demand identification information and a second real element;

optimizing thread parameters of the cloud office big data identification thread based on the first thread operation index and the second thread operation index.

Preferably, the invoking the cloud office big data identification thread obtains interaction element distribution of second hot spot office interaction data and third hot spot office interaction data in the cloud office big data to be processed based on the second original interaction element distribution, and the invoking includes:

calling the cloud office big data identification thread to obtain a second significant alternative interaction behavior set of the sample cloud office big data based on the second original interaction element distribution, and taking office interaction data corresponding to the second significant alternative interaction behavior set in the sample cloud office big data as second hot spot office interaction data;

calling the cloud office big data identification thread to acquire the interaction element distribution of the third hot spot office interaction data based on the second significant alternative interaction behavior set and the second original interaction element distribution;

after the invoking of the cloud office big data identification thread obtains the interaction element distribution of the third hotspot office interaction data based on the second significant alternative interaction behavior set and the second original interaction element distribution, the method further includes:

calling the cloud office big data identification thread to acquire detection interaction element distribution and error interaction element distribution corresponding to interaction element distribution of the third hot spot office interaction data, wherein the detection interaction element distribution corresponding to the interaction element distribution of the third hot spot office interaction data is used for representing that the second significant alternative interaction behavior set belongs to detection results of various types, and the error interaction element distribution corresponding to the interaction element distribution of the third hot spot office interaction data is used for representing deviation of the second significant office interaction behavior set relative to the second significant alternative interaction behavior set;

acquiring a third thread running index of the cloud office big data identification thread based on a comparison result between a detection interactive element distribution corresponding to the interactive element distribution of the third hot spot office interactive data and a third real element, and acquiring a fourth thread running index of the cloud office big data identification thread based on a comparison result between an error interactive element distribution corresponding to the interactive element distribution of the third hot spot office interactive data and a fourth real element;

optimizing thread parameters of the cloud office big data identification thread based on the third thread operation index and the fourth thread operation index.

The scheme of one embodiment of the application provides an artificial intelligence server, which comprises 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 big data processing method and/or process for cloud office applications, according to some embodiments of the present application;

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

FIG. 3 is a block diagram of an exemplary big data processing system for cloud office applications, shown in accordance with some embodiments of the present application, an

FIG. 4 is a diagram illustrating the hardware and software components of an exemplary artificial intelligence server, according to some embodiments of the present application.

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.

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

The whole scheme of the big data processing method and the artificial intelligence server applied to cloud office can be summarized as follows: the cloud office big data to be processed is analyzed and recognized through the cloud office big data recognition thread, so that a first significant office interaction behavior set, interaction elements of each office interaction data segment in the first hot spot office interaction data and intention demand interaction elements of each office event in the first hot spot office interaction data are obtained, and a collaborative office recognition result is determined. Therefore, compared with a mode of directly performing cooperative office identification on the interactive element distribution of the first hot spot office interactive data in the related art, the scheme can be used for landing on the interactive elements of the office interactive data fragments and the intention demand interactive elements of office events, so that the accuracy of the cooperative office identification result is ensured, the cooperative office identification result is ensured to be matched with the actual office business scene and office business demand as far as possible, and a basis for making a decision credible is provided for the subsequent update and upgrade of office service software.

The above aspects will be further explained with reference to the drawings and possible examples, and for the convenience of the following description, the following is an explanation of the related technical features.

(1) Cloud office big data identification thread: artificial intelligence based machine learning models/machine learning Networks such as Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), Long Short-Term Memory Networks (LSTM).

(2) Configuring a cloud office big data identification thread: and training the cloud office big data identification thread.

(3) Thread running indexes are as follows: the loss function (loss function) or the cost function (cost function) of the cloud office big data identification thread is a function which maps a random event or a value of a related random variable of the random event into a non-negative real number to represent the risk or loss of the random event. In application, the loss function is usually associated with the optimization problem as a learning criterion, i.e. the model is solved and evaluated by minimizing the loss function.

(4) Thread parameters: the cloud office big data identifies relevant model parameters of the thread, such as weight (weight) and bias (bias).

It is understood that the description of other technical features will be made in conjunction with the following practical embodiments, and is not exhaustive herein.

First, an exemplary big data processing method applied to cloud office is described, please refer to fig. 1, which is a flowchart illustrating an exemplary big data processing method and/or process applied to cloud office according to some embodiments of the present application, and the big data processing method applied to cloud office may include the technical solutions described in the following steps S11-S13. It should be noted that the acquisition of the cloud office big data to be processed is authorized by the relevant business user, in other words, the authorization authentication is performed between the artificial intelligence server and the relevant office business terminal in advance.

Step S11, the artificial intelligence server calls a cloud office big data identification thread to obtain a first remarkable office interaction behavior set in the cloud office big data to be processed, and determines first hot spot office interaction data in the cloud office big data to be processed and interaction element distribution of the first hot spot office interaction data.

For example, the artificial intelligence server may call the cloud office big data recognition thread from the local, or call the cloud office big data recognition thread from the cloud, and the cloud office big data recognition thread may be configured/trained in advance. The cloud office big data to be processed can be actively acquired from an office business terminal by an artificial intelligence server, and can also be uploaded to the artificial intelligence server by the office business terminal.

For another example, the set of significant office interaction behaviors may be a set formed by a plurality of office interaction behaviors with higher feature recognition degrees, such as office interaction behaviors with higher feature recognition degrees being office interaction behaviors ac1, ac2, ac3, ac4 and ac5, and then the first set of significant office interaction behaviors may be { ac1, ac2, ac3, ac4, ac5 }.

In addition, the hotspot office interaction data may be office interaction data with a high popularity and/or search index, such as remote operations based on office projects, such as remote video conferences, such as multi-user editing operations, and the like. Based on this, the interactive elements may be understood as data features of the hotspot office interaction data, and the interactive element distribution may be understood as a feature map or a feature distribution list for recording the interactive elements, but is not limited thereto.

In some possible embodiments, the invoking of the cloud office big data identification thread described in step S11 above obtains a first significant office interaction behavior set in the to-be-processed cloud office big data, and determines first hot spot office interaction data and interaction element distribution of the first hot spot office interaction data in the to-be-processed cloud office big data, which may be implemented by the following technical solutions described in steps S111 to S113.

And step S111, importing the cloud office big data to be processed into a cloud office big data identification thread.

For example, the cloud office big data to be processed can be adaptively adjusted according to a data format corresponding to the cloud office big data identification thread, then the cloud office big data after the adaptability adjustment is transmitted to the cloud office big data identification thread, and then corresponding data processing and analysis are performed through the cloud office big data identification thread.

Step S112, calling the cloud office big data identification thread to obtain a first significant office interaction behavior set in the cloud office big data to be processed.

In practical implementation, in order to ensure the integrity of the first significant office interaction behavior set, the extraction of the first significant office interaction behavior set may be performed based on the interaction element distribution. Based on this, the invoking of the cloud office big data identification thread described in step S112 above to obtain the first significant office interaction behavior set in the to-be-processed cloud office big data may include the following technical solutions described in step S1121 and step S1122.

Step S1121, calling the cloud office big data identification thread to obtain first original interaction element distribution in the cloud office big data to be processed.

In the embodiment of the application, the first original interaction element distribution can be understood as a basic feature map, and is used for recording data features of cloud office big data to be processed.

Step S1122, invoking the cloud office big data identification thread to obtain a first significant office interaction behavior set in the to-be-processed cloud office big data based on the first original interaction element distribution.

It can be understood that by analyzing the first original interaction element distribution, data characteristics of the cloud office big data to be processed can be comprehensively identified, so that the integrity of the first significant office interaction behavior set is ensured.

In some possible embodiments, the invoking of the cloud office big data recognition thread described in the above step S1122 to obtain the first significant office interaction behavior set in the to-be-processed cloud office big data based on the first original interaction element distribution may be implemented by the following technical solution described in steps S1122 a-S1122 c.

Step S1122a, the cloud office big data identification thread is called to obtain a first significant alternative interaction behavior set in the to-be-processed cloud office big data based on the first original interaction element distribution.

It can be understood that, since the first original interaction element distribution covers a larger number of interaction elements, which may include some noise, in order to ensure the integrity of the first significant alternative interaction behavior set and reduce the noise ratio, the first significant alternative interaction behavior set may be obtained by rough screening.

Step S1122b, the cloud office big data identification thread is called to obtain, based on the first significant alternative interaction behavior set and the first original interaction element distribution, an interaction element distribution of second hot spot office interaction data in the to-be-processed cloud office big data.

In this embodiment of the application, a difference between the first significant alternative interaction behavior set and the first original interaction element distribution may be analyzed, so as to determine second hot spot office interaction data in the to-be-processed cloud office big data, so as to further determine interaction element distribution of the second hot spot office interaction data. It is understood that the second hotspot office interaction data is not identical to the first hotspot office interaction data, and generally, the first hotspot office interaction data is included in the second hotspot office interaction data. It can be understood that the interaction element distribution of the second hot spot office interaction data in the cloud office big data to be processed is obtained, so that the fine screening of the interaction element distribution can be realized, and the noise is reduced as much as possible.

Step S1122c, the cloud office big data recognition thread is called to obtain the first significant office interaction behavior set based on the interaction element distribution of the second hot spot office interaction data.

It can be understood that, by performing error analysis on the interactive element distribution of the second hot spot office interaction data, the noise ratio can be reduced on the premise of ensuring the integrity of the first significant office interaction behavior set, and to achieve this, the step S1122c described above for invoking the cloud office big data identification thread to obtain the first significant office interaction behavior set based on the interactive element distribution of the second hot spot office interaction data may be implemented by the following technical solutions: calling the cloud office big data identification thread to acquire detection interaction element distribution and error interaction element distribution corresponding to interaction element distribution of the second hot spot office interaction data; and acquiring the information of the first significant office interaction behavior set based on the detection interaction element distribution corresponding to the interaction element distribution of the second hot spot office interaction data and the error interaction element distribution corresponding to the interaction element distribution of the second hot spot office interaction data.

In a related embodiment, the detection interaction element distribution is used to indicate that the first significant alternative interaction behavior set belongs to each type of detection result, and the error interaction element distribution is used to indicate a deviation of the first significant office interaction behavior set with respect to the first significant alternative interaction behavior set. It can be understood that, by determining the detected interactive element distribution and the error interactive element distribution corresponding to the interactive element distribution of the second hotspot office interaction data, the deviation of the first significant office interaction behavior set from the first significant alternative office interaction behavior set can be taken into account, so that the noise ratio can be reduced on the premise of ensuring the integrity of the first significant office interaction behavior set.

In other possible embodiments, the information about the first significant office interaction activity set further includes an association of the first significant office interaction activity set and a type of the first significant office interaction activity set. Based on this, the obtaining of the information of the first significant office interaction behavior set based on the detected interaction element distribution corresponding to the interaction element distribution of the second hot spot office interaction data and the error interaction element distribution corresponding to the interaction element distribution of the second hot spot office interaction data described in the above steps may include the following contents: performing threshold screening on detection interactive element distribution corresponding to the interactive element distribution of the second hot spot office interactive data to obtain the type of the first significant office interactive behavior set; and performing deviation correction on the association condition of the error interaction element distribution corresponding to the interaction element distribution of the second hotspot office interaction data and the first remarkable alternative interaction behavior set to obtain the association condition of the first remarkable office interaction behavior set.

For example, the interactive elements may include numerical elements for quantitatively describing different features, and the association of the first set of significant office interactive behaviors may be understood as an association relationship between office interactive behaviors in the first set of significant office interactive behaviors. It can be understood that the type of the first significant office interaction behavior set can be accurately positioned by performing threshold screening, and then the association condition of the first significant office interaction behavior set can be completely obtained by performing deviation correction on the error interaction element distribution corresponding to the interaction element distribution of the second hot spot office interaction data and the association condition of the first significant alternative office interaction behavior set. It can be seen that the information of the first significant office interaction behavior set can include the type of the first significant office interaction behavior set and the association condition of the first significant office interaction behavior set.

Step S113, calling the cloud office big data identification thread to acquire first hot spot office interaction data and interaction element distribution of the first hot spot office interaction data in the cloud office big data to be processed based on the first remarkable office interaction behavior set.

In this embodiment of the application, the first hot spot office interaction data is office interaction data corresponding to the first significant office interaction behavior set in the to-be-processed cloud office big data. It can be understood that the first significant office interaction behavior set is further identified and analyzed, so that the identification accuracy of the first hot spot office interaction data and the interaction element distribution of the first hot spot office interaction data is improved.

Step S12, the artificial intelligence server calls the cloud office big data identification calling thread to split the first hot office interactive data into a plurality of office interactive data fragments, extracts an interactive element corresponding to each office interactive data fragment in the first hot office interactive data by combining with the interactive element distribution of the first hot office interactive data, and obtains an intention demand interactive element of each office event in the first hot office interactive data.

For example, the office interaction data fragments may be split according to the time sequence characteristics, or may be split according to the office projects, which is not limited in the embodiments of the present application. By splitting the first hot spot office interaction data into a plurality of office interaction data fragments, interaction elements of the office interaction data fragments and intention demand interaction elements of office events can be landed on, and therefore the accuracy of a follow-up cooperative office identification result is guaranteed. In addition, an office event can be understood as a different office business item, and the intent requirement interaction element of the office event is used for characterizing the intent requirement characteristics of the office event, such as the related office requirement characteristics.

In a related embodiment, the invoking of the cloud office big data identification thread described in step S12 splits the first hot spot office interaction data into a plurality of office interaction data segments, extracts, in combination with the interaction element distribution of the first hot spot office interaction data, an interaction element corresponding to each office interaction data segment in the first hot spot office interaction data, and obtains an intention requirement interaction element of each office event in the first hot spot office interaction data, which may include contents described in the following technical solutions: calling the cloud office big data identification thread to split the first hot spot office interactive data into a plurality of office interactive data fragments, calling the cloud office big data identification thread to extract an interactive element corresponding to each office interactive data fragment in the first hot spot office interactive data based on the interactive element distribution of the first hot spot office interactive data, and calling the cloud office big data identification thread to obtain an intention demand interactive element of each office event in the first hot spot office interactive data.

In some examples, the interaction element corresponding to the office interaction data segment is a detection result of significant office interaction behavior existing in the office interaction data segment. The detection result can be understood as the probability that the office interaction behavior is significant in the office interaction data segment. The cloud office big data identification thread is called to split the first hot spot office interaction data into a plurality of office interaction data fragments, interaction elements corresponding to each office interaction data fragment in the first hot spot office interaction data are extracted based on the interaction element distribution of the first hot spot office interaction data, and the intention demand interaction elements of each office event in the first hot spot office interaction data can be acquired through the related network layer of the cloud office big data identification thread.

Based on some of the above embodiments, the information of the first significant office interaction behavior set may include a correlation of the first significant office interaction behavior set. Based on this, the calling the cloud office big data identification thread to acquire the intention demand interaction element of each office event in the first hotspot office interaction data, which is described in the above steps, can be implemented by the following implementation modes: calling the cloud office big data identification thread to identify intention requirements of the first original interaction element distribution to obtain interaction element distribution corresponding to first intention requirement identification information corresponding to each office event in the cloud office big data to be processed; determining, based on the association condition of the first significant office interaction behavior set, an interaction element corresponding to each office event in the first hot spot office interaction data in the interaction element distribution corresponding to the first intention demand identification information, as an intention demand interaction element corresponding to the office event in the first hot spot office interaction data.

For example, intention demand recognition can be performed on the first original interaction element distribution through an intention demand recognition layer or an intention demand recognition sub-thread in the cloud office big data recognition thread, so that interaction element distribution corresponding to the first intention demand recognition information corresponding to each office event in the cloud office big data to be processed is obtained. It can be understood that the first intention requirement identification information is used for representing the requirements of the office users reflected in the operation process of the office event, and the interaction element distribution corresponding to the first intention requirement identification information can highlight the requirements of the office users more accurately.

Further, the interaction element corresponding to each office event in the first hot spot office interaction data in the interaction element distribution corresponding to the first intention requirement identification information may be queried by using the association condition of the first significant office interaction behavior set as a reference, or may be understood as: and matching each office event in the first hot spot office interaction data with the interaction elements in the interaction element distribution corresponding to the first intention demand identification information, so that the intention demand interaction elements of the office events in the first hot spot office interaction data can be accurately determined, and disorder between the office events and the intention demand interaction elements is avoided.

Step S13, the artificial intelligence server obtains a collaborative office identification result based on the interaction element of each office interaction data segment in the first hot spot office interaction data, the information of the first significant office interaction behavior set, and the intention requirement interaction element of each office event in the first hot spot office interaction data.

In the embodiment of the application, the cooperative office identification result is used for reflecting the business matching condition between different office interaction objects (equipment/users) from a global level or an integral level. For example, the cooperative office identification result may represent the office resource calling condition in the same office scene, may also represent the office scene relevancy in the same office resource calling state, and may also represent whether resource calling or scene adaptation conflicts exist between office demands of different office interactive objects, so that a credible decision basis can be provided for subsequent update and upgrade of office service software.

In some possible embodiments, the information about the first significant office interaction behavior set may include a type of the first significant office interaction behavior set, and based on this, the obtaining of the collaborative office identification result based on the interaction element of each office interaction data segment in the first hot spot office interaction data, the information about the first significant office interaction behavior set, and the intention requirement interaction element of each office event in the first hot spot office interaction data, which are described in the above step S13, may be implemented by the following technical solutions described in the steps S131 and S132.

Step S131, determining office interaction data with the significant office interaction behavior in the first hot spot office interaction data based on the interaction element corresponding to each office interaction data segment in the first hot spot office interaction data, and determining a type corresponding to the office event in the first hot spot office interaction data based on an intention requirement interaction element of each office event in the first hot spot office interaction data.

In the embodiment of the application, the interaction elements corresponding to the office interaction data segments corresponding to the office interaction data with the significant office interaction behavior are larger than the preset detection result threshold value. The preset detection result threshold value can be set according to an actual situation, for example, the value range is 0-1, taking the preset detection result threshold value as 0.8 as an example, if the quantitative value corresponding to the interactive element corresponding to the office interactive data segment is greater than 0.8, it is determined that the office interactive data to which the office interactive data segment belongs has a significant office interactive behavior.

Further, the type of the office event corresponding to the first hot spot office interaction data can be determined according to the difference of the intention demand interaction elements of each office event in the first hot spot office interaction data, so that the accurate classification of the type of the office event is ensured.

Step S132, determining, based on the type of each office event in the first hot spot office interaction data, the office event belonging to the type of the first significant office interaction behavior set in the office interaction data with significant office interaction behavior, as the collaborative office identification result.

For example, the type of each office event in the first hotspot office interaction data may be analyzed, so as to determine the office events in the office interaction data with significant office interaction behaviors, which correspond to/match the type of the first significant office interaction behavior set, and then, relevant event features of the office events are extracted and integrated to obtain a collaborative office identification result. It can be understood that, the office events belonging to the type of the first significant office interaction behavior set in the office interaction data with significant office interaction behaviors are generally related to more office interaction objects/office events, so that it can be ensured that the cooperative office identification result reflects service matching conditions between different office interaction objects (devices/users) from a global level, thereby providing a reliable decision basis for subsequent update and upgrade of office service software.

In the above manner, the cloud office big data identification thread acquires a first significant office interaction behavior set in the cloud office big data to be processed, acquires a first original interaction element distribution of the cloud office big data to be processed and an interaction element distribution of the first hot spot office interaction data based on the first significant office interaction behavior set, office interaction behavior recognition of office interaction data fragmentation is carried out on the first hotspot office interaction data, therefore, the analysis and identification of the significant office interaction behavior in the first hotspot office interaction data can be quickly realized, and calling a cloud office big data identification thread to acquire an intention demand interaction element of each office event in the first hot spot office interaction data, therefore, the cooperative office identification result can be obtained by combining the analysis identification result of the significant office interaction behavior in the first hot spot office interaction data and the intention requirement interaction element of each office event. Compared with a mode of directly performing cooperative office identification on the interactive element distribution of the first hot spot office interactive data in the related technology, the scheme can be used for landing on the interactive elements of the office interactive data fragments and the intention demand interactive elements of office events, so that the accuracy of the cooperative office identification result is ensured, and the cooperative office identification result is ensured to be matched with the actual office business scene and the office business demand as far as possible, so that a credible decision basis is provided for the subsequent update and upgrade of office service software.

In addition, because the interactive element content in the interactive element distribution of the corresponding first hot spot office interactive data is obtained in a manner of directly performing cooperative office identification on the interactive element distribution of the first hot spot office interactive data, the data volume corresponding to the output interactive element distribution is large, and the cloud office big data identification thread in the application only analyzes and identifies whether office interactive behaviors exist in the office interactive data segments, the input and output quantity of data can be effectively reduced, so that computer resources (such as a memory) occupied by cloud office big data identification and the time spent by the cloud office big data identification are effectively reduced, and the efficiency of cloud office big data identification is improved.

In some optional embodiments, before the step of invoking the cloud office big data identification thread to acquire the first significant office interaction behavior set in the to-be-processed cloud office big data described in step S112, the method may further include a technical solution of configuring the cloud office big data identification thread.

In some optional embodiments, the step of configuring the cloud office big data identification thread may be implemented by the following technical solutions: importing sample cloud office big data into the cloud office big data identification thread; calling the cloud office big data identification thread to obtain second original interaction element distribution of the sample cloud office big data; calling the cloud office big data identification thread to obtain the interaction element distribution of second hot spot office interaction data and third hot spot office interaction data in the sample cloud office big data based on the second original interaction element distribution; calling the cloud office big data identification thread to divide the second hot spot office interaction data into a plurality of office interaction data fragments, calling the cloud office big data identification thread to extract interaction elements corresponding to each office interaction data fragment in the second hot spot office interaction data based on the interaction element distribution of the third hot spot office interaction data, and calling the cloud office big data identification thread to perform intention demand identification on the second original interaction element distribution so as to obtain interaction element distribution corresponding to second intention demand identification information; acquiring a first thread operation index of the cloud office big data identification thread based on a comparison result between an interaction element corresponding to each office interaction data segment in the second hot spot office interaction data and a first real element, and acquiring a second thread operation index of the cloud office big data identification thread based on a comparison result between interaction element distribution corresponding to the second intention demand identification information and a second real element; optimizing thread parameters of the cloud office big data identification thread based on the first thread operation index and the second thread operation index.

In some examples, the real element may be used as a reference for performing configuration optimization on the cloud office big data identification thread, for example, a thread running index (model loss) is determined through the real element (true value) and the interactive element (predicted value), and then a thread parameter (model parameter) of the cloud office big data identification thread is adjusted and optimized through the thread running index (model loss) so as to achieve configuration optimization on the cloud office big data identification thread.

In some possible examples, the invoking of the cloud office big data recognition thread described in the above steps to obtain the interaction element distribution of the second hot spot office interaction data and the third hot spot office interaction data in the to-be-processed cloud office big data based on the second original interaction element distribution may include the following: calling the cloud office big data identification thread to obtain a second significant alternative interaction behavior set of the sample cloud office big data based on the second original interaction element distribution, and taking office interaction data corresponding to the second significant alternative interaction behavior set in the sample cloud office big data as second hot spot office interaction data; and calling the cloud office big data identification thread to acquire the interaction element distribution of the third hot spot office interaction data based on the second significant alternative interaction behavior set and the second original interaction element distribution.

In some possible examples, after the step of invoking the cloud office big data recognition thread to obtain the interaction element distribution of the third hotspot office interaction data based on the second significant alternative interaction behavior set and the second original interaction element distribution described in the above step, the method may further include the following steps: calling the cloud office big data identification thread to acquire detection interaction element distribution and error interaction element distribution corresponding to interaction element distribution of the third hot spot office interaction data; acquiring a third thread running index of the cloud office big data identification thread based on a comparison result between a detection interactive element distribution corresponding to the interactive element distribution of the third hot spot office interactive data and a third real element, and acquiring a fourth thread running index of the cloud office big data identification thread based on a comparison result between an error interactive element distribution corresponding to the interactive element distribution of the third hot spot office interactive data and a fourth real element; optimizing thread parameters of the cloud office big data identification thread based on the third thread operation index and the fourth thread operation index.

In some examples, a detection interaction element distribution corresponding to the interaction element distribution of the third hotspot office interaction data is used to indicate that the second significant alternative interaction behavior set belongs to each type of detection result, and an error interaction element distribution corresponding to the interaction element distribution of the third hotspot office interaction data is used to indicate a deviation of the second significant office interaction behavior set with respect to the second significant alternative interaction behavior set.

In some optional embodiments, after obtaining the collaborative office identification result described in the step S13, the method may further include updating and upgrading the relevant office service software. The content regarding the update and upgrade of the relevant office service software can be realized by the content described in the following step S14.

In some optional embodiments, the updating and upgrading of the target office service software through the global scenario distribution information and the global demand distribution information described in the above step S14 may be implemented by the following technical solutions described in steps S141 to S144.

Step S141, obtaining a target office service item set to be updated and upgraded corresponding to the target office service software according to the matching result between the global scene distribution information and the global demand distribution information; and respectively carrying out output service identification and input service identification on a plurality of office service items in the target office service item set to obtain an output service identification result set and an input service identification result set.

For example, the matching result between the global scene distribution information and the global demand distribution information may be a one-to-one correspondence relationship between members in different distribution information, so that a target office service item set to be updated and upgraded may be accurately determined. The output class service can be understood as a resource issuing service, and the input class service can be understood as a resource uploading service.

Step S142, carrying out first screening processing on the output service identification result set through a first preset screening instruction to obtain a first office service item subset including output services; and carrying out second screening processing on the input service identification result set through a second preset screening instruction to obtain a second office service item subset comprising the input service.

For example, different screening indications correspond to different screening strategies.

Step S143, performing consistency optimization processing based on the first office service item subset and the second office service item subset, to obtain a target office service item subset matching the target service in the target office service item set.

In an embodiment of the present application, the target service includes at least one of an output class service and an input class service, and the target office service item subset is used for updating and upgrading the target office service item set.

For example, the consistency optimization process may be a deduplication/merge analysis process performed on the first subset of office service items and the second subset of office service items, so as to ensure the compactness of the target subset of office service items.

And step S144, updating and upgrading the target office service item set based on the target office service item subset.

It can be understood that by positioning the target office service item subset, the more important office service items in the target office service item set can be updated and upgraded, thereby reducing unnecessary resource waste and improving the updating and upgrading efficiency of the office service items.

In some alternative embodiments, the performing, in step S141, output class service identification and input class service identification on a plurality of office service items in the target office service item set respectively to obtain an output class service identification result set and an input class service identification result set may include the following contents: respectively carrying out output service identification on a plurality of office service items in the target office service item set to obtain output service identification contents in each office service item and original item service types corresponding to the output service identification contents; determining an output service identification result set based on the output service identification content in each office service item and the corresponding original item service type; and respectively carrying out input class service identification on a plurality of office service matters in the target office service matter set to obtain an input class service identification result set.

In this way, the output class service identification content and the original item service type in each office service item are independently analyzed, so that the output class service identification result set can be ensured to have higher feature identification degree.

In some optional embodiments, the performing, by the above step, input class service identification on each of the plurality of office service items in the target office service item set to obtain an input class service identification result set may include the following: respectively carrying out service scene recognition on a plurality of office service items in the target office service items to obtain service scene recognition results corresponding to the office service items; respectively carrying out service function identification on a plurality of office service items in the target office service items to obtain service function identification results corresponding to the office service items; associating the service scene identification result and the service function identification result corresponding to the same office state; and performing input service identification processing based on the service function identification result associated with the target service scene identification result in the target office service item to obtain an input service identification result set.

In this way, by performing service scene recognition and service function recognition on the office service items, correlation of relevant recognition results can be performed from a service scene level and a service function level, thereby ensuring that the input service recognition result set can be matched with the actual office business.

Next, in view of the above big data processing method applied to cloud office, an exemplary big data processing apparatus applied to cloud office is further provided in the embodiments of the present invention, as shown in fig. 2, the big data processing apparatus 200 applied to cloud office may include the following functional modules.

The interaction element determining module 210 is configured to invoke a cloud office big data identification thread to obtain a first significant office interaction behavior set in the cloud office big data to be processed, and determine first hot spot office interaction data in the cloud office big data to be processed and interaction element distribution of the first hot spot office interaction data.

The data fragment splitting module 220 is configured to call the cloud office big data identification thread to split the first hot spot office interaction data into a plurality of office interaction data fragments, extract an interaction element corresponding to each office interaction data fragment in the first hot spot office interaction data in combination with the interaction element distribution of the first hot spot office interaction data, and acquire an intention demand interaction element of each office event in the first hot spot office interaction data.

The identification result obtaining module 230 is configured to obtain a collaborative office identification result based on an interaction element of each office interaction data segment in the first hot spot office interaction data, information of the first significant office interaction behavior set, and an intention requirement interaction element of each office event in the first hot spot office interaction data.

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

The artificial intelligence server 10 calls a cloud office big data identification thread to acquire a first significant office interaction behavior set in to-be-processed cloud office big data of the office business terminal 20, and determines first hot spot office interaction data in the to-be-processed cloud office big data and interaction element distribution of the first hot spot office interaction data; calling the cloud office big data identification thread to split the first hot spot office interactive data into a plurality of office interactive data fragments, extracting interactive elements corresponding to each office interactive data fragment in the first hot spot office interactive data by combining with the interactive element distribution of the first hot spot office interactive data, and acquiring intention demand interactive elements of each office event in the first hot spot office interactive data; and acquiring a cooperative office identification result based on the interaction element of each office interaction data fragment in the first hot spot office interaction data, the information of the first significant office interaction behavior set and the intention demand interaction element of each office event in the first hot spot office interaction data.

Further, referring to fig. 4 in conjunction, the artificial intelligence 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 artificial intelligence server 10 may include more or fewer components than shown in FIG. 4 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 cloud office big data identification method is applied to an artificial intelligence server, and comprises the following steps:

2. The method according to claim 1, wherein the calling a cloud office big data recognition thread to obtain a first significant office interaction behavior set in the cloud office big data to be processed and determine first hot spot office interaction data and interaction element distribution of the first hot spot office interaction data in the cloud office big data to be processed comprises:

3. The method of claim 2, wherein the information of the first significant office interaction behavior set comprises a type of the first significant office interaction behavior set, and the obtaining of the collaborative office identification result based on the interaction element of each office interaction data segment in the first hotspot office interaction data, the information of the first significant office interaction behavior set, and the intention requirement interaction element of each office event in the first hotspot office interaction data comprises:

4. The method according to claim 2, wherein the invoking the cloud office big data recognition thread to obtain a first set of significant office interaction behaviors in the cloud office big data to be processed comprises:

5. The method of claim 4, wherein the information about the first significant office interaction activity set comprises a correlation of the first significant office interaction activity set, and the invoking the cloud office big data recognition thread to obtain an intention requirement interaction element for each office event in the first hotspot office interaction data comprises:

6. The method of claim 4, wherein the invoking the cloud office big data recognition thread to obtain a first set of significant office interaction behaviors in the cloud office big data to be processed based on the first original interaction element distribution comprises:

7. The method of claim 6, wherein the invoking the cloud office big data recognition thread to obtain the first set of significant office interaction behaviors based on the interaction element distribution of the second hotspot office interaction data comprises:

8. The method according to claim 2, further comprising, before the step of invoking the cloud office big data recognition thread to obtain a first set of significant office interaction behaviors in the pending cloud office big data: configuring the cloud office big data identification thread;

9. The method according to claim 8, wherein the invoking the cloud office big data recognition thread to obtain the interaction element distribution of the second hot spot office interaction data and the third hot spot office interaction data in the cloud office big data to be processed based on the second original interaction element distribution comprises:

10. An artificial intelligence 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.