CN115062594A

CN115062594A - Method, device, equipment and medium for generating work log based on artificial intelligence

Info

Publication number: CN115062594A
Application number: CN202210353748.4A
Authority: CN
Inventors: 黄彬莹
Original assignee: Shenzhen Jinwei Kaibo Information Technology Co ltd
Current assignee: Shenzhen Jinwei Kaibo Information Technology Co ltd
Priority date: 2022-04-06
Filing date: 2022-04-06
Publication date: 2022-09-16

Abstract

The embodiment of the application provides a method, a device, equipment and a medium for generating a working log based on artificial intelligence, wherein a first data subset which is document type data is automatically analyzed and obtained to obtain a first working log data subset based on the artificial intelligence technology, a second data subset which is attendance type data is obtained to obtain a second working log data subset, a third data subset which is picture type data is obtained to obtain a third working log data subset, and finally the first working log data subset, the second working log data subset and the third working log data subset are automatically combined to obtain working log report data.

Description

Method, device, equipment and medium for generating working log based on artificial intelligence

Technical Field

The embodiment of the application relates to the technical field of artificial intelligence, in particular to a method, a device, equipment and a medium for generating a working log based on artificial intelligence.

Background

At present, when enterprise employees form work reports by recording work contents of the week, the month or the year, the statistics and the arrangement are generally carried out in a manual arrangement mode, and omission exists possibly, so that the accuracy of the work report data obtained based on the manual arrangement mode is low, and the efficiency is low.

Disclosure of Invention

The embodiment of the application provides a method and a device for generating a work log based on artificial intelligence and a storage medium, and aims to solve the problems that in the prior art, work report data obtained based on a manual sorting mode is low in accuracy and efficiency.

In a first aspect, an embodiment of the present application provides a method for generating a work log based on artificial intelligence from the perspective of a cloud server, where the method includes:

when the time interval between the current system time and the last working log generation time is determined to be equal to a preset first time period, generating a working log data screening time interval according to the current system time and the last working log generation time, and acquiring user identity information;

acquiring a user working log demand data type set according to the user position type in the user identity information; the user work log requirement data type set at least comprises document type data, attendance type data and picture type data;

generating a current screening condition according to the user working log demand data type set and the working log data screening time interval, and acquiring a target screening data set corresponding to the user identity information according to the current screening condition;

acquiring a first data subset which is document type data in the target screening data set, and extracting keywords of each document data in the first data subset according to a preset keyword screening strategy to obtain task data corresponding to each document data to form a first working log data subset;

acquiring a second data subset which is attendance type data in the target screening data set, and performing data combination on each attendance data included in the second data subset according to a date ascending order to obtain a second working log data subset;

acquiring a third data subset which is picture type data in the target screening data set, and acquiring an image recognition result set corresponding to the third data subset according to a pre-trained image recognition model to form a third working log data subset;

and combining the first working log data subset, the second working log data subset and the third working log data subset to obtain working log report data.

In a second aspect, an embodiment of the present application further provides an artificial intelligence based work log generating apparatus, where the artificial intelligence based work log generating apparatus includes:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for generating a working log data screening time interval according to the current system time and the last working log generation time and acquiring user identity information when the time interval between the current system time and the last working log generation time is determined to be equal to a preset first time period;

the second acquisition module is used for acquiring a user working log demand data type set according to the user position type in the user identity information; the user work log requirement data type set at least comprises document type data, attendance type data and picture type data;

the data screening module is used for generating current screening conditions according to the user working log demand data type set and the working log data screening time interval, and acquiring a target screening data set corresponding to the user identity information according to the current screening conditions;

the first extraction module is used for acquiring a first data subset which is document type data in the target screening data set, extracting keywords of each document data in the first data subset according to a preset keyword screening strategy, and obtaining task data corresponding to each document data to form a first working log data subset;

the second extraction module is used for acquiring a second data subset which is attendance type data in the target screening data set, and performing data combination on each attendance data included in the second data subset according to a date ascending sequence to obtain a second working log data subset;

the third extraction module is used for acquiring a third data subset which is picture type data in the target screening data set, and acquiring an image recognition result set corresponding to the third data subset according to a pre-trained image recognition model to form a third working log data subset;

and the log report generation module is used for combining the first working log data subset, the second working log data subset and the third working log data subset to obtain working log report data.

In a third aspect, an embodiment of the present application further provides a processing device, which includes a processor and a memory, where the memory stores a computer program, and the processor executes, when calling the computer program in the memory, the steps in any one of the artificial intelligence based work log generation methods provided in the embodiments of the present application.

In a fourth aspect, the present application further provides a computer-readable storage medium, where a plurality of instructions are stored, and the instructions are suitable for being loaded by a processor to perform the steps in any one of the artificial intelligence based work log generation methods provided in the present application.

According to the method and the device, the first data subset which is document type data is automatically analyzed and obtained to obtain the first working log data subset, the second data subset which is attendance type data is obtained to obtain the second working log data subset, the third data subset which is picture type data is obtained to obtain the third working log data subset, and finally the first working log data subset, the second working log data subset and the third working log data subset are automatically combined to obtain working log report data.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic flow chart of a method for artificial intelligence based work log generation in the present application;

FIG. 2 is a schematic diagram of an artificial intelligence based log generation apparatus according to the present application;

FIG. 3 is a schematic diagram of a processing apparatus according to the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

In the description that follows, specific embodiments of the present application will be described with reference to steps and symbols executed by one or more computers, unless otherwise indicated. Accordingly, these steps and operations will be referred to herein, in several instances, as being performed by a computer, the embodiments of the present application are directed to computer-implemented processes involving operations performed by computer-processing units that represent electronic signals representing data in a structured form. This operation transforms the data or maintains it at locations in the computer's memory system, which may be reconfigured or otherwise altered in a manner well known to those skilled in the art. The data maintains a data structure that is a physical location of the memory that has particular characteristics defined by the data format. However, while the principles of the application have been described in language specific to above, it is not intended to be limited to the specific form set forth herein, and it will be recognized by those of ordinary skill in the art that various of the steps and operations described below may be implemented in hardware.

The principles of the present application may be employed in numerous other general-purpose or special-purpose computing, communication environments or configurations. Examples of well known computing systems, environments, and configurations that may be suitable for use with the application include, but are not limited to, hand-held telephones, personal computers, servers, multiprocessor systems, microcomputer-based systems, mainframe-based computers, and distributed computing environments that include any of the above systems or devices.

The terms "first", "second", and "third", etc. in this application are used to distinguish between different objects and not to describe a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion.

The method for generating a working log based on artificial intelligence provided by the present application is described below.

Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a method for generating a work log based on artificial intelligence according to the present application, where the method is applied to a cloud server. The method provided by the application specifically comprises the following steps:

s110, when the time interval between the current system time and the last working log generation time is determined to be equal to a preset first time period, generating a working log data screening time interval according to the current system time and the last working log generation time, and acquiring user identity information.

In the embodiment of the application, the execution subject involved is a cloud server, a first type user side, a second type user side and a card punching terminal. The cloud server is provided with an office automation system, and can acquire data respectively uploaded by the first type user side, the second type user side and the card punching terminal to perform centralized processing, so that working log report data is obtained. The first type server is a portable mobile intelligent terminal (such as a smart phone, a notebook computer, a tablet computer, and the like), and can store a first data subset of document type data and a third data subset of picture type data, and periodically upload the first data subset and the third data subset to the cloud server for further data processing. The second type server is a non-portable mobile intelligent terminal (such as a desktop computer and the like), and can also store the first data subset of the document type data and the third data subset of the picture type data, and periodically upload the first data subset and the third data subset to the cloud server for further data processing. The card punching terminal (also understood as an attendance terminal) is a face recognition card punching device, a fingerprint recognition card punching device and the like, and can acquire attendance data of a user and upload the attendance data to the cloud server for further data processing.

The technical scheme is described by taking the cloud server as an execution main body, so that in order to periodically and automatically generate the working log report data in the cloud server, whether a time interval between the current system time and the last working log generation time (the last working log generation time is 24: 00 in the last Friday, or 24: 00 in the last month, etc.) is equal to a preset first time period or not needs to be judged (for example, if the first time period is set to 7 days, the generated working log report data corresponds to the working data weekly report; for example, if the first time period is set to 28, 29, 30, or 31 days, the generated working log report data corresponds to the working data monthly report; of course, the first time period can also be set to a time value of one year or even longer, that is, the first time period is set according to the actual use requirement of a user).

For example, the first time period is set to 7 days as an example. When the time interval between the current system time and the last working log generation time is determined to be equal to the preset first time period, the time point when the working log report data can be generated is reached, and the working log report data in the cost period is required to be acquired for which user, so that the working log data screening time interval is required to be generated according to the current system time and the last working log generation time, and the user identity information is acquired. For example, a dedicated storage area is allocated to different users in the cloud server, and data uploaded by each user based on the first type user side, the second type user side, and the card punching terminal is stored in a private storage space corresponding to the user. It should be noted that the acquisition, storage, application, etc. of the personal information referred to in the present application are in accordance with the regulations of the relevant law, and necessary security measures are taken without violating the customs of the official order. And the private storage space corresponding to each user is the user identity information of the known user. Therefore, the initial working log data screening time interval and the user identity information are obtained based on the cloud server, and data screening conditions can be effectively generated so as to more accurately screen and obtain data.

In one embodiment, step S110 includes:

taking the last working log generation time as an initial time point, taking the current system time as an end time point, and taking a time period between the initial time point and the end time point as a working log data screening time interval;

acquiring user login information corresponding to a current data storage area, and correspondingly acquiring user identity information according to a user information set included in the user login information; the user information set at least comprises user account data and user identity information; the user identity information at least comprises user name, user gender, user age, user job number, user job type and job duty remark information.

In an embodiment of the present application, for example, the first time period is set to 7 days, and the current system time corresponds to 20XX years XX1 month XX2 day 24: 00 and corresponds to a day of friday, and the last work log generation time corresponds to 20XX years XX3 months XX4 days 24: 00, if the judgment result shows that the number of the 20XX year is XX1 month XX2 day 24: 00 and 20XX year XX3 month XX4 day 24: the time interval between 00 is 7 days, then with a 20XX 3 month XX4 day 24: 00 is the starting time point and is given in 20XX year XX1 month XX2 day 24: 00 is an end time point, and a time period between the start time point and the end time point is used as the working log data screening time interval, namely 20XX year XX3 month XX4 day 24: 00-20XX year XX1 month XX2 day 24: 00.

and then acquiring working log report data of which user in a cost cycle is generated by the cloud server, so that user login information corresponding to the current data storage area of the extracted data by the cloud server can be acquired, and user identity information is correspondingly acquired based on a user information set included in the user login information. Specifically, the user information set at least includes user account data (for example, information including a character string corresponding to a user account, i.e., a user nickname, etc.) and user identity information, and the user identity information at least includes a user name, a user gender, a user age, a user job number, a user job type, and job duty remark information; the user job types comprise a first job type (generally understood to be a business member role or a salesman role in an enterprise, and the main responsibility of the staff is to sell products) corresponding to the business job types, and also comprise a second job type (generally understood to be a research and development staff role in the enterprise, and the main responsibility of the staff is to research and develop projects) corresponding to the technical support job types, and main work task items of the job types are described in job role remark information corresponding to each user job type. Therefore, the data screening conditions can be generated quickly by the method.

S120, acquiring a user work log demand data type set according to the user position type in the user identity information; the user work log requirement data type set at least comprises document type data, attendance type data and picture type data.

In the embodiment of the application, because the job role remark information corresponding to each user job type is pre-stored in the cloud server, a user work log required data type set can be obtained based on the user job type, specifically, the user work log required data type set is formed by the user work log required data types such as daily work editing documents (such as project required books), contract documents, attendance data, working photos and the like. It can be understood that the daily work editing document and the contract document of the user are document type data, the attendance data is attendance type data, and the work photo is picture type data. Therefore, a corresponding user work log demand data type set is generated based on the user position type, and the demanded data can be screened out from the user data stored in the cloud server.

In one embodiment, step S120 includes:

when the user position type is determined to be a first position type, acquiring a user work log demand data type set corresponding to the first position type; wherein the first position type is a business position type;

when the user position type is determined to be a second position type, acquiring a user work log demand data type set corresponding to the second position type; wherein the second job type is a technical support job type.

In the embodiment of the application, when the position type of the user is determined to be a first position type corresponding to the business position type, the user work log required data types which are generally and collectively included in the user work log required data type include three types, namely contract documents, work photos and attendance data; and when the user position type is determined to be a second position type corresponding to the technical support position type, the user work log requirement data types which are generally included in the user work log requirement data type set comprise three user daily work editing documents, work photos and attendance data. Therefore, different user work log demand data type sets are generated in the cloud server based on users with different job types, data can be more accurately screened and processed according to the job types of the users, all data are not required to be processed, and data processing efficiency can be effectively improved.

S130, generating a current screening condition according to the user work log demand data type set and the work log data screening time interval, and acquiring a target screening data set corresponding to the user identity information according to the current screening condition.

In the embodiment of the application, when a target user (such as a user a) for which user identity information is intended obtains a corresponding user working log demand data type set and the working log data screening time interval, the data type set and the working log data screening time interval are combined together to generate a current screening condition. And then, based on the current screening condition, the user A carries out data retrieval in the corresponding exclusive storage area of the cloud server to obtain a target screening data set of the user A. The target screening data set comprises a first data subset including document type data, a second data subset including attendance type data and a third data subset including picture type data. Therefore, the target data of the user can be more accurately screened based on the current screening condition formed by time and the characteristic dimension of the user so as to assist in generating the working log report data.

S140, a first data subset which is document type data in the target screening data set is obtained, keyword extraction is carried out on each document data in the first data subset according to a preset keyword screening strategy, and task data corresponding to each document data are obtained to form a first working log data subset.

In the embodiment of the application, since the target screening dataset at least includes the first data subset of the document type data, the second data subset of the attendance type data, and the third data subset of the picture type data, at this time, keyword extraction may be performed on the first data subset of the document type data according to a preset keyword screening policy, and task data corresponding to each document data is obtained to form the first work log data subset.

For example, when the user a uses the first type user side to work at an office workstation or an outwork place (such as a place where a visited client is located), or when the user a uses the second type user side to work at an office workstation, the edited document type data can be understood as cloud document edited data, and the data can be synchronized with a current data storage area (that is, an exclusive storage area corresponding to the user a) in the cloud server in time, that is, data such as specific document content, document name, and document modification time (the document modification time refers to the time when a certain document is modified and stored last time) of the document type data edited by the user using the first type user side or the second type user side can be synchronously uploaded to the cloud server. Therefore, the week of the user A corresponds to the first data subset in the target screening data set, and the document type working content of the week of the user A can be quickly generated as a data sample.

Since the specific content in each document is not required to be embodied when the document type working content of the week of the user a is generated specifically, in order to extract the document type working content of the week of the user a quickly, the keyword extraction may be performed on each document data included in the first data subset according to a preset keyword screening policy, and the task data corresponding to each document data is obtained to form the first work log data subset. The keyword screening strategy is used for extracting Chinese document names of document data to form document task data, or extracting a plurality of core keywords of document contents to form document task data.

In one embodiment, step S140 includes:

acquiring the ith document data in the first data subset, and acquiring the document modification time of the ith document data; wherein the initial value of i is 1, the value range of i is [1, N1], and N1 represents the total number of the document data included in the first data subset;

if the document name of the i-th document data is determined to be a Chinese name, acquiring the document name of the i-th document data as a keyword of the i-th document data according to the keyword screening strategy, and forming i-th task data by the keyword of the i-th document data and the document modification time of the i-th document data;

if the document name of the i-th document data is determined to be a digital name, acquiring a text of the i-th document data, acquiring an i-th core keyword combination corresponding to the text of the i-th document data according to the keyword screening strategy, and forming i-th task data by the i-th core keyword combination and the document modification time of the i-th document data;

the value of i is updated by adding 1 to the value of i;

if it is determined that i does not exceed N1, returning to the step of acquiring the i-th document data in the first data subset and acquiring the document modification time of the i-th document data;

and if the i exceeds N1, acquiring the task data from the 1 st task to the N1 th task to form a first working log data subset.

In the embodiment of the present application, a complete acquisition process of the task data No. 1 is taken as an example for explanation. Specifically, the document data No. 1 in the first data subset is obtained, and the document modification time of the document data No. 1 is obtained (for example, with continued reference to the above example, the document modification time should be between 24: 00 in XX3 month XX4 and 24: 00 in XX1 month XX2 and 24: 00 in XX year).

Then, it is judged whether the document name of the document data No. 1 is a Chinese name (e.g., XXX project specification) or a numerical name (e.g., 12). If the document name of the No. 1 document data is determined to be the Chinese name, the document name indicates that the document is subjected to standard naming by the user A aiming at the document based on the preset task specification, so that the document name of the No. 1 document data can be obtained based on the keyword screening strategy and directly used as the keyword of the No. 1 document data, the content of the specific document of the No. 1 document data does not need to be extracted to extract the keyword, and the method for directly obtaining the Chinese name of the No. 1 document data can be more efficient and accurate.

If the document name of the No. 1 document data is determined to be a digital name, the document name indicates that the document is not named by the user A based on a preset task specification, if the document name of the No. 1 document data is directly used as a keyword of the No. 1 document data, the task content cannot be directly embodied, at this time, a No. 1 core keyword combination corresponding to the text of the No. 1 document data is obtained according to the keyword screening strategy, and the No. 1 core keyword combination and the document modification time of the No. 1 document data form No. 1 task data. When the core key word combination No. 1 corresponding to the text of the document data No. 1 is obtained according to the keyword screening policy, the text of the document data No. 1 may be subjected to word segmentation processing, keyword extraction processing based on a TF-IDF model (i.e., a word frequency-inverse text frequency index model), and a core key word combination No. 1 corresponding to the text of the document data No. 1, which is formed by screening the first 3-digit keywords from the keyword set according to a preset number of keyword screening (e.g., set to 3) of the TF-IDF values, so that the task data No. 1 is formed by the core key word combination No. 1 and the document modification time of the document data No. 1. Or when the core key word combination No. 1 corresponding to the text of the document data No. 1 is obtained according to the keyword screening policy, the text abstract (generally within 20 words) of the text of the document data No. 1 is directly extracted as the core key word combination No. 1 based on an LDA model (i.e. a hidden dirichlet distribution model, which is also a topic model), and finally the task data No. 1 is formed by the core key word combination No. 1 and the document modification time of the document data No. 1. And by analogy, the task data No. 2 of the document data No. 2 in the first data subset is continuously acquired until the task data No. N1 of the document data No. N1 is acquired, so that the first work log data subset is formed.

S150, a second data subset which is the attendance type data in the target screening data set is obtained, and data merging is carried out on each attendance data in the second data subset according to the ascending order of dates to obtain a second working log data subset.

In an embodiment of the application, the attendance type data of the user a stored in the general cloud server is obtained by the card punching terminal and uploaded to the current data storage area corresponding to the user a in the cloud server, and the time of the card punching data corresponding to the obtained second data subset is 20XX year XX3 month XX4 day 24: 00-20XX year XX1 month XX2 day 24: 00. At this time, the attendance data included in the second data subset may be subjected to data merging in an ascending order of date, and combined into a second work log data subset composed of the attendance data. Therefore, based on the mode, the target attendance data can be extracted quickly.

In one embodiment, step S150 includes:

acquiring a jth attendance data subset in the second data subset; wherein the initial value of j is 1, the value range of j is [1, N2], and N2 represents the total days of the first time period;

acquiring a jth day attendance identification corresponding to the jth day attendance data subset based on a preset daily working time period; the j-th attendance identification is one of a normal attendance identification and an abnormal attendance identification;

combining the jth attendance time point of the jth day attendance data subset with the jth day attendance identification to obtain jth attendance data;

the value of j is updated by adding 1 to the value of j;

if j is determined not to exceed N2, returning to execute the step of acquiring the j-th attendance data subset in the second data subset;

and if j exceeds N2, acquiring the attendance data from the No. 1 attendance data to the No. N2 attendance data to form a second working log data subset.

In the embodiment of the present application, a complete acquisition process of attendance data No. 1 is taken as an example for description. Specifically, the 1 st day attendance data subset (including the 1 st day attendance time point and the 1 st day attendance time point) in the second data subset is obtained first, and then the 1 st day attendance identifier corresponding to the 1 st day attendance data subset is obtained based on the preset daily working time period. Wherein the preset daily working time period is 9: 00-18: 00, when the attendance identification of the 1 st day is obtained, specifically, whether the attendance time point on the 1 st day is 9 points ahead and whether the attendance time point on the 1 st day off is 18: 00, if it is determined that the attendance time point on day 1 is before 9 and the attendance time point on day 1 off duty is 18: after 00, judging that the 1 st day attendance identification corresponding to the 1 st day attendance data subset is a normal attendance identification; if the 1 st day attendance time point is determined to be after 9 o' clock or the 1 st day attendance time point is 18: before 00, the 1 st day attendance identification corresponding to the 1 st day attendance data subset is judged to be abnormal attendance identification. At this time, the 1 st day attendance time point and the 1 st day attendance identifier corresponding to the 1 st day attendance data subset are known, and the 1 st day attendance data can be obtained by combining the 1 st day attendance time point, the 1 st day attendance time point and the 1 st day attendance identifier corresponding to the 1 st day attendance data subset. And continuing to acquire the attendance data 2 of the attendance data subset on the 2 nd day in the second data subset until the attendance data N2 of the attendance data subset on the N2 th day is acquired, so that a second working log data subset is formed. Therefore, the attendance data can be conveniently and clearly displayed in the follow-up process based on the mode of acquiring the attendance data day by day.

And S160, acquiring a third data subset which is the picture type data in the target screening data set, and acquiring an image recognition result set corresponding to the third data subset according to a pre-trained image recognition model to form a third working log data subset.

In an embodiment of the present application, the picture type data of the user a stored in the general cloud server is a work photo collected by the user who visits a client (co-photos with the client or takes a foreground photo of a client company, etc.) when the user goes out or visits some products that can be authorized to take photos, and is uploaded to the current data storage area corresponding to the user a in the cloud server, and the shooting time of the picture type data corresponding to the obtained third data subset is located 24 of XX3 month XX4 day 20 XX: 00-20XX year XX1 month XX2 day 24: 00. At this time, each picture included in the third data subset may be subjected to picture recognition result extraction based on a pre-trained image recognition model (such as an image recognition model of a convolutional neural network, an object detection network, and the like) to form a third work log data subset. Therefore, based on the mode, the specific work items of the work picture can be extracted quickly.

In one embodiment, step S160 includes:

acquiring a kth image in the third data subset; wherein the initial value of k is 1, the value range of k is [1, N3], and N3 represents the total number of pictures in the third data subset;

acquiring an image recognition type of the kth image based on the image recognition model; the image identification type is one of a site picture type, a person picture type, a document picture type or an object picture type;

if the image identification type of the kth image is determined to be the type of the image, acquiring shooting location information and shooting time of the kth image, and forming kth image information by the shooting location information and the shooting time of the kth image;

if the image identification type of the kth image is determined to be the type of the figure picture, obtaining the unique figure number and the shooting time of the kth image, and forming kth picture information by the unique figure number and the shooting time of the kth image;

if the image recognition type of the kth image is determined to be a document image type, acquiring a text recognition result and shooting time of the kth image, and forming kth image information by the text recognition result and the shooting time of the kth image;

if the image identification type of the kth image is determined to be an object picture type, acquiring an object identification result and shooting time of the kth image, and forming kth picture information by the object identification result and the shooting time of the kth image;

the value of k is updated by adding 1 to the value of k;

if the k is determined not to exceed N3, returning to the step of acquiring the kth image in the third data subset;

if j exceeds N3, the picture information No. 1 to N3 are obtained to form a third working log data subset.

In the embodiment of the present application, the complete acquisition process of the 1 st image is taken as an example for explanation. Specifically, the 1 st image in the third data subset is obtained first, and then the picture type and the specific picture recognition result of the 1 st image are obtained based on the image recognition model, so that the work content is extracted from the work picture. Since the image identification type of the 1 st image is one of a place picture type, a person picture type, a document picture type or an object picture type, if the image identification type of the 1 st image is determined to be the place picture type (generally, if the image is detected to have no classification such as human body, document and product, the classification can be determined to be the place picture type), the shooting place information and the shooting time of the 1 st image are obtained, and the shooting place information and the shooting time of the 1 st image form the picture information No. 1; when a first type of user terminal with a camera takes a picture to obtain a shot picture, the picture attribute data (such as information including shooting time, shooting location, and the like) is known, and the shooting location information and the shooting time can be quickly obtained by reading the picture attribute data.

If the image identification type of the 1 st image is determined to be a person image type (generally, the image is detected to have a person, and no classifications of a site scene, a document and a product exist, the image identification type can be determined to be a person image type), the person unique number and the shooting time of the 1 st image are obtained, and the person unique number and the shooting time of the 1 st image form the No. 1 image information. In generating the unique number of the person in the 1 st image, the unique number of the person may be formed by adding the shooting time and date to the current photo shooting number (for example, the 1 st image is the first shot photo in the present day), so that the number of the person photos is 20XX 3 month XX5 day 01 as the unique number of the person, and then the unique number is compared with the number of the person photos in 20XX 3 month XX5 day HH 1: the MM1: SS1 shooting time is combined to obtain the picture information No. 1.

If the figure picture type of the 1 st image is determined to be a document picture type (generally, documents are detected to exist in the picture, and no classification of human bodies, places, scenes and products exists, the type of the document picture can be determined), a text recognition result of the 1 st image is obtained based on an image recognition model (such as a convolution cyclic neural network model included in the image, namely a CRNN model), shooting time is obtained according to picture attribute data, and the text recognition result and the shooting time of the 1 st image form picture information 1.

If the image identification type of the 1 st image is determined to be a real object image type (generally, a product real object is detected to appear in the image, and no classification such as a human body, a document and a real scene of a place exists, the image identification type can be determined to be the real object image type), an object identification result (if the object identification result is the product 1) of the 1 st image is obtained based on an image identification model (such as an object detection network included in the image, more specifically, a single-lens multi-box detector model, namely an SSD model), shooting time is obtained according to image attribute data, and the object identification result and the shooting time of the 1 st image form No. 1 image information. Therefore, based on the mode of specifically identifying the type of the working photo and the content of the specific photo, other working matters of the non-text editing class can be displayed more clearly in the follow-up process.

S170, combining the first working log data subset, the second working log data subset and the third working log data subset to obtain working log report data.

In the embodiment of the present application, after the first working log data subset, the second working log data subset, and the third working log data subset of the user (user a in the above example) are obtained in the cloud server, the first working log data subset, the second working log data subset, and the third working log data subset are finally and automatically combined to obtain the working log report data. Therefore, the data processing method is obtained after analyzing and summarizing all types of data based on the user, the user does not need to collect and arrange the working data, and the data processing efficiency is improved.

In one embodiment, step S170 includes:

acquiring picture information with document picture types in the first working log data subset and the third working log data subset to form a working content item report data set;

acquiring picture information with a place picture type in the second working log data subset and the third working log data subset to form an attendance report data set;

acquiring picture information with a figure picture type in the third working log data subset, and acquiring picture information with an object picture type in the third working log data subset to form an auxiliary working content item report data set;

and combining the work content item report data set, the attendance item report data set and the auxiliary work content item report data set to obtain work log report data.

In an embodiment of the application, since the working pictures included in the third working log data subset may be identified as customer visiting pictures, real object shooting pictures, document shooting pictures (such as memo notes of a meeting) or real scene place shooting pictures of a user, after further analyzing the working pictures included in the third working log data subset, picture information of a place picture type in the third working log data subset may be further combined with the second working log data subset as auxiliary attendance data to obtain an attendance report data set; combining the picture information with the character picture type and the picture information with the object picture type in the third work log data subset to form an auxiliary work content item report data set; and combining the picture information with the document picture type in the third working log data subset with the first working log data subset to form a working content item report data set. Finally, the work content item report data set, the attendance item report data set and the auxiliary work content item report data set are combined, and more specifically, the combined data are filled into corresponding filling areas in a preset work log report template (a work content item report data set filling area, an attendance item report data set filling area and an auxiliary work content item report data set filling area are arranged in the work log report template), so that work log report data are obtained. Therefore, the report data is generated based on the automatic filling mode without manual sorting, so that the data dimension is more, and the efficiency is higher.

The method realizes automatic combination of the first working log data subset, the second working log data subset and the third working log data subset to obtain the working log report data, does not need manual sorting, improves the working log data acquisition efficiency and improves the data accuracy.

In order to better implement the method of the present application, an embodiment of the present application further provides an artificial intelligence based working log generation apparatus 100.

Referring to fig. 2, fig. 2 is a schematic structural diagram of an artificial intelligence based work log generating apparatus 100 according to the present application, wherein the artificial intelligence based work log generating apparatus 100 may specifically include the following structures: the system comprises a first acquisition module 110, a second acquisition module 120, a data filtering module 130, a first extraction module 140, a second extraction module 150, a third extraction module 160, and a log report generation module 170.

The first obtaining module 110 is configured to, when it is determined that a time interval between a current system time and a previous working log generation time is equal to a preset first time period, generate a working log data screening time interval according to the current system time and the previous working log generation time, and obtain user identity information.

In the embodiment of the application, the related terminals include a cloud server, a first type user side, a second type user side and a card punching terminal. The cloud server is provided with an office automation system, and can acquire data respectively uploaded by the first type user side, the second type user side and the card punching terminal to perform centralized processing, so that working log report data is obtained. The first type server is a portable mobile intelligent terminal (such as a smart phone, a notebook computer, a tablet computer, and the like), and can store a first data subset of document type data and a third data subset of picture type data, and periodically upload the first data subset and the third data subset to the cloud server for further data processing. The second type server is a non-portable mobile intelligent terminal (such as a desktop computer and the like), and can also store the first data subset of the document type data and the third data subset of the picture type data, and periodically upload the first data subset and the third data subset to the cloud server for further data processing. The card punching terminal (also understood as an attendance terminal) is a face recognition card punching device, a fingerprint recognition card punching device and the like, and can acquire attendance data of a user and upload the attendance data to the cloud server for further data processing.

For example, the present application is described with the first time period set to 7 days as an example. When the time interval between the current system time and the last working log generation time is equal to the preset first time period, the time point that the working log report data can be generated is reached, and the working log report data in the cost period of which user is required to be generated is required to be acquired, so that the working log data screening time interval is required to be generated according to the current system time and the last working log generation time, and the user identity information is acquired. For example, a dedicated storage area is allocated to different users in the cloud server, and data uploaded by each user based on the first type user side, the second type user side, and the card punching terminal is stored in a private storage space corresponding to the user. It should be noted that the acquisition, storage, application, etc. of the personal information referred to in the present application are in accordance with the regulations of the relevant law, and necessary security measures are taken without violating the customs of the official order. And the private storage space corresponding to each user is the user identity information of the known user. Therefore, the initial working log data screening time interval and the user identity information are obtained based on the cloud server, and data screening conditions can be effectively generated so as to more accurately screen and obtain data.

In an embodiment, the first obtaining module 110 is specifically configured to:

In an embodiment of the present application, for example, the first time period is set to 7 days, and the current system time corresponds to 20XX years XX1 month XX2 day 24: 00 and corresponds to a day of friday, and the last work log generation time corresponds to 20XX year XX3 month XX4 day 24: 00, if the judgment result shows that the number of the 20XX year is XX1 month XX2 day 24: 00 and 20XX year XX3 month XX4 day 24: the time interval between 00 is 7 days, then 24 in 20XX year XX3 month XX 4: 00 is the starting time point and is given in 20XX year XX1 month XX2 day 24: 00 is an end time point, and a time period between the start time point and the end time point is used as the working log data screening time interval, namely 20XX year XX3 month XX4 day 24: 00-20XX year XX1 month XX2 day 24: 00.

and then acquiring working log report data of which user in a cost cycle is generated by the cloud server, so that user login information corresponding to the current data storage area of the extracted data by the cloud server can be acquired, and user identity information is correspondingly acquired based on a user information set included in the user login information. Specifically, the user information set at least includes user account data (for example, information including a character string corresponding to a user account, i.e., a user nickname, etc.) and user identity information, and the user identity information at least includes a user name, a user gender, a user age, a user job number, a user job type, and job duty remark information; the user job types comprise a first job type (generally understood to be a business member role or a salesman role in an enterprise, and the main responsibility of the employees is to sell products) corresponding to the business job types and a second job type (generally understood to be a research and development personnel role in the enterprise, and the main responsibility of the employees is to research and develop projects) corresponding to the technical support job types, and main job task items of the job types are described in job memo information corresponding to each user job type. Therefore, the data screening conditions can be generated quickly by the method.

A second obtaining module 120, configured to obtain a user job log requirement data type set according to a user job position type in the user identity information; the user work log requirement data type set at least comprises document type data, attendance type data and picture type data.

In an embodiment, the second obtaining module 120 is specifically configured to:

And the data screening module 130 is configured to generate a current screening condition according to the user work log required data type set and the work log data screening time interval, and obtain a target screening data set corresponding to the user identity information according to the current screening condition.

In the embodiment of the application, when a target user (such as a user a) for which user identity information is intended obtains a corresponding user working log demand data type set and the working log data screening time interval, the data type set and the working log data screening time interval are combined together to generate a current screening condition. And then, based on the current screening condition, the user A carries out data retrieval in the corresponding exclusive storage area of the cloud server to obtain a target screening data set of the user A. The target screening dataset comprises a first data subset including document type data, a second data subset including attendance type data and a third data subset including picture type data. Therefore, the target data of the user can be more accurately screened based on the current screening condition formed by time and the characteristic dimension of the user so as to assist in generating the working log report data.

The first extraction module 140 is configured to obtain a first data subset that is document type data in the target screening data set, perform keyword extraction on each piece of document data included in the first data subset according to a preset keyword screening policy, and obtain task data corresponding to each piece of document data to form a first work log data subset.

In the embodiment of the application, since the target screening dataset at least includes the first data subset of the document type data, the second data subset of the attendance type data, and the third data subset of the picture type data, at this time, keyword extraction may be performed on the first data subset of the document type data according to a preset keyword screening policy, so as to obtain task data corresponding to each document data to form the first work log data subset.

In an embodiment, the first extraction module 140 is specifically configured to:

the value of i is updated by adding 1 to the value of i;

and if the i exceeds N1, acquiring the task data No. 1 to the task data No. N1 to form a first work log data subset.

Then, it is judged whether the document name of the document data No. 1 is a Chinese name (e.g., XXX project specification) or a numerical name (e.g., 12). If the document name of the No. 1 document data is determined to be a Chinese name, the document name indicates that the document is subjected to standard naming by the user A aiming at the document based on the preset task specification, so that the document name of the No. 1 document data can be obtained based on the keyword screening strategy and directly used as the keyword of the No. 1 document data, the content of the specific document of the No. 1 document data does not need to be extracted to extract the keyword, and the Chinese name of the No. 1 document data can be obtained directly more efficiently and accurately.

The second extraction module 150 is configured to obtain a second data subset, which is attendance type data in the target screening data set, and perform data merging on each attendance data included in the second data subset according to a date ascending order to obtain a second work log data subset.

In an embodiment, the second extraction module 150 is specifically configured to:

the value of j is updated by adding 1 to the value of j;

A third extraction module 160, configured to obtain a third data subset that is picture type data in the target screening data set, and obtain an image recognition result set corresponding to the third data subset according to a pre-trained image recognition model, so as to form a third work log data subset.

In the embodiment of the present application, the picture type data of the user a stored in the general cloud server is a working picture collected by the user through the first type user side when the user visits the client (cooperates with the client or takes a picture of the foreground of the client company, etc.) or visits some products that can be authorized to take pictures, and is uploaded to the current data storage area corresponding to the user a in the cloud server, and the shooting time of the picture type data corresponding to the obtained third data subset is located 24 days XX3 month XX4 in 20XX year: 00-20XX year XX1 month XX2 day 24: 00. At this time, each picture included in the third data subset may be subjected to picture recognition result extraction based on a pre-trained image recognition model (such as an image recognition model of a convolutional neural network, an object detection network, and the like) to form a third work log data subset. Therefore, based on the mode, the specific work items of the work picture can be extracted quickly.

In an embodiment, the third extraction module 160 is specifically configured to:

if the image identification type of the kth image is determined to be a document image type, acquiring a text identification result and shooting time of the kth image, and forming kth image information by the text identification result and the shooting time of the kth image;

the value of k is updated by adding 1 to the value of k;

If the image identification type of the 1 st image is determined to be a person image type (generally, the image is detected to have a person, and no classification such as a location scene, a document and a product exists, the image can be determined to be a person image type), the person unique number and the shooting time of the 1 st image are obtained, and the person unique number and the shooting time of the 1 st image form the No. 1 image information. In generating the person unique number of the 1 st image, the person unique number may be formed by adding the current photograph shooting number (for example, the 1 st image is the first photograph taken in the present day) to the date corresponding to the shooting time, so that the person unique number is 20XX 3 month XX5 day 01 person photograph, which is further similar to 20XX 3 month XX5 day HH 1: MM1: SS1 as photographing time, and combining the photographing time to obtain the information of No. 1 picture.

A log report generating module 170, configured to combine the first working log data subset, the second working log data subset, and the third working log data subset to obtain working log report data.

In an embodiment, the log report generating module 170 is specifically configured to:

In an embodiment of the application, since the working pictures included in the third working log data subset may be identified as customer visiting pictures, real object shooting pictures, document shooting pictures (such as meeting memo minutes) or real scene place shooting pictures of the user, after further analyzing the working pictures included in the third working log data subset, the picture information of the type of the place picture in the third working log data subset may be further used as auxiliary attendance data to be merged with the second working log data subset to obtain an attendance report data set; combining the picture information with the character picture type and the picture information with the object picture type in the third work log data subset to form an auxiliary work content item report data set; and combining the picture information with the document picture type in the third working log data subset with the first working log data subset to form a working content item report data set. Finally, the work content item report data set, the attendance item report data set and the auxiliary work content item report data set are combined, and more specifically, the combined data are filled into corresponding filling areas in a preset work log report template (a work content item report data set filling area, an attendance item report data set filling area and an auxiliary work content item report data set filling area are arranged in the work log report template), so that work log report data are obtained. Therefore, the report data is generated based on the automatic filling mode without manual sorting, so that the data dimension is more, and the efficiency is higher.

The device realizes automatic combination of the first working log data subset, the second working log data subset and the third working log data subset to obtain the working log report data, manual arrangement is not needed, the working log data acquisition efficiency is improved, and the data accuracy is improved.

The present application further provides a processing device, and referring to fig. 3, fig. 3 shows a schematic structural diagram of the processing device of the present application, and specifically, the processing device of the present application includes a processor, and the processor is configured to implement the steps in the embodiment corresponding to fig. 1 when executing the computer program stored in the memory; alternatively, the processor is configured to implement the functions of the modules in the corresponding embodiment as shown in fig. 3 when executing the computer program stored in the memory.

Illustratively, a computer program may be partitioned into one or more modules/units, which are stored in a memory and executed by a processor to accomplish the present application. One or more modules/units may be a series of computer program instruction segments capable of performing certain functions, the instruction segments being used to describe the execution of a computer program in a computer device.

The processing device may include, but is not limited to, a processor, a memory. Those skilled in the art will appreciate that the illustration is merely an example of a processing device and is not meant to be limiting, and that more or fewer components than those illustrated may be included, or some components may be combined, or different components may be included, for example, the processing device may also include input output devices, network access devices, buses, etc., through which the processor, memory, input output devices, network access devices, etc., are connected.

The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the processor being the control center for the processing device and the various interfaces and lines connecting the various parts of the overall processing device.

The memory may be used to store computer programs and/or modules, and the processor may implement various functions of the computer device by executing or executing the computer programs and/or modules stored in the memory, as well as by invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, video data, etc.) created according to the use of the processing device, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.

The display screen is used for displaying characters of at least one character type output by the input and output unit.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the apparatus, the processing device and the corresponding modules thereof described above may refer to the description in the embodiment corresponding to fig. 1, and are not described herein again in detail.

It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.

To this end, embodiments of the present application provide a computer-readable storage medium, where a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in the embodiment corresponding to fig. 1 in the present application, and specific operations may refer to the description in the embodiment corresponding to fig. 1, and are not described herein again.

Wherein the computer-readable storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.

Since the instructions stored in the computer-readable storage medium can execute the steps in the embodiment of the present application corresponding to fig. 1, the beneficial effects that can be achieved in the embodiment of the present application corresponding to fig. 1 can be achieved, and the detailed description is omitted here.

The method, the device and the storage medium for generating the working log based on artificial intelligence provided by the application are introduced in detail, a specific example is applied in the embodiment of the application to explain the principle and the implementation mode of the application, and the description of the embodiment is only used for helping to understand the method and the core idea of the application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A method for generating a working log based on artificial intelligence, which is characterized by comprising the following steps:

2. The method of claim 1, wherein generating a working log data filtering time interval according to the current system time and the last working log generation time, and obtaining user identity information comprises:

3. The method of claim 1, wherein obtaining a set of user job log requirements data types based on user job types in the user identity information comprises:

4. The method according to claim 1, wherein the performing keyword extraction on each document data included in the first data subset according to a preset keyword screening policy to obtain task data corresponding to each document data to form a first work log data subset comprises:

acquiring the ith document data in the first data subset, and acquiring the document modification time of the ith document data; the initial value of i is 1, the value range of i is [1, N1], and N1 represents the total number of the document data included in the first data subset;

the value of i is updated by adding 1 to the value of i;

if it is determined that i does not exceed N1, returning to the step of acquiring the ith document data in the first data subset and acquiring the document modification time of the ith document data;

5. The method of claim 1, wherein the data merging the attendance data included in the second data subset in ascending order of date to obtain a second work log data subset comprises:

the value of j is updated by adding 1 to the value of j;

6. The method of claim 1, wherein obtaining a set of image recognition results corresponding to the third subset of data according to a pre-trained image recognition model to form a third subset of work log data comprises:

acquiring an image identification type of the kth image based on the image identification model; the image identification type is one of a site picture type, a person picture type, a document picture type or an object picture type;

the value of k is updated by adding 1 to the value of k;

7. The method of claim 6, wherein combining the first, second, and third subsets of the work log data to obtain work log report data comprises:

acquiring picture information with a site picture type in the second working log data subset and the third working log data subset to form an attendance report data set;

8. An artificial intelligence-based work log generation apparatus, comprising:

9. A processing device comprising a processor and a memory, a computer program being stored in the memory, the processor performing the method according to any of claims 1 to 7 when calling the computer program in the memory.

10. A computer-readable storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the method of any one of claims 1 to 7.