CN113642984A - Employee attendance checking method, device, equipment and storage medium based on artificial intelligence - Google Patents
Employee attendance checking method, device, equipment and storage medium based on artificial intelligence Download PDFInfo
- Publication number
- CN113642984A CN113642984A CN202110874816.7A CN202110874816A CN113642984A CN 113642984 A CN113642984 A CN 113642984A CN 202110874816 A CN202110874816 A CN 202110874816A CN 113642984 A CN113642984 A CN 113642984A
- Authority
- CN
- China
- Prior art keywords
- attendance
- result
- employee
- distance
- electronic fence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q10/1091—Recording time for administrative or management purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Remote Sensing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of artificial intelligence, and discloses an employee attendance method, device, equipment and storage medium based on artificial intelligence, wherein the method comprises the following steps: respectively acquiring employee position data corresponding to each employee data in an employee data set by adopting a preset time interval; respectively calculating the distance between the position data of each employee and the boundary of the target electronic fence to obtain a first distance set; carrying out attendance judgment according to each first distance in the first distance set and a first preset threshold value respectively to obtain a single attendance result to be stored corresponding to each first distance; and updating the single attendance result library according to each single attendance result to be stored. The attendance checking method and the system realize automatic acquisition of employee position data at preset time intervals for attendance result calculation without requiring employee fixed-point card punching, can perform attendance management for private outing after card punching, and also avoid difficulty in accurate card punching by adopting a card refilling flow when the employee forgets to punch the card.
Description
Technical Field
The present application relates to the field of artificial intelligence technology, and in particular, to a method, an apparatus, a device and a storage medium for employee attendance based on artificial intelligence.
Background
In the prior art, employee attendance adopts fixed-point card punching methods such as card punching software, worker card punching, fingerprint card punching, facial recognition and the like, and the fixed-point card punching method has the following problems: (1) after the employee is checked out, the attendance management can not be carried out when the employee goes out privately; (2) the situation that the employee forgets to punch the card often occurs, so that the card needs to be punched by a supplementary punching process; (3) some employees go out to eat and/or rest at noon, in order to ensure that the employees still go to work on time in the afternoon, the employees are required to punch cards in the afternoon and the afternoon, so that the employees need to punch the cards at least four times a day, the employees who do not go out at noon are not friendly, and the employees who punch the cards at least four times a day often forget to punch the cards or directly do not punch the cards, so that the difficulty of attendance management is further increased; (4) for a branch company or a subsidiary company built outside the field, the number of people working in an office is small, and accurate additional card punching is difficult to be carried out by adopting an additional card punching process.
Disclosure of Invention
The application mainly aims to provide an employee attendance method, an employee attendance device, employee attendance equipment and a storage medium based on artificial intelligence, and aims to solve the technical problems that in the prior art, a fixed-point card punching method is adopted to perform employee attendance, attendance management cannot be performed on a person who goes out privately after card punching is completed, and accurate card punching is difficult to perform through a card re-punching flow when an employee forgets to punch a card.
In order to achieve the above object, the present application provides an employee attendance method based on artificial intelligence, the method comprising:
acquiring a target electronic fence, wherein the target electronic fence is generated by adopting an electronic fence generation model, and the electronic fence generation model is a model obtained based on machine learning;
acquiring a staff data set, and respectively acquiring staff position data corresponding to each staff data in the staff data set by adopting a preset time interval;
respectively calculating the distance between each employee position data and the boundary of the target electronic fence to obtain a first distance set;
acquiring a first preset threshold, and performing attendance judgment according to each first distance in the first distance set and the first preset threshold respectively to obtain a single attendance result to be stored corresponding to each first distance;
and updating the single attendance result library according to each single attendance result to be stored.
Further, the step of obtaining the target electronic fence includes:
acquiring an electronic fence generating signal, wherein the electronic fence generating signal carries a target office address;
responding to the electronic fence generation signal, and acquiring a data set of attendance staff according to the target office address;
acquiring a staff home address according to the attendance staff data set to obtain a staff home address set to be processed;
vector generation is carried out on the employee home address set to be processed, and address feature vectors to be processed are obtained;
and inputting the address feature vector to be processed into the electronic fence generation model to generate an electronic fence, so as to obtain the target electronic fence.
Further, before the step of acquiring the target electronic fence, the method further includes:
obtaining a plurality of training samples, the training samples comprising: address sample feature vectors and fence calibrations;
inputting a plurality of training samples into a machine learning model to perform electronic fence generation, and obtaining electronic fence predicted values corresponding to the training samples;
determining a training target according to the difference between the predicted value of the electronic fence and the calibrated value of the electronic fence;
and aiming at the direction of minimizing the value of the training target, adjusting the model parameters of the machine learning model and continuing training until a machine learning end condition is reached, and determining the machine learning model reaching the machine learning end condition as the electronic fence generation model.
Further, the step of performing attendance judgment according to each first distance in the first distance set and the first preset threshold value respectively to obtain a single attendance result to be stored corresponding to each first distance includes:
when the first distance is smaller than or equal to the first preset threshold, determining that the single attendance result to be stored corresponding to each first distance smaller than or equal to the first preset threshold is determined as attendance;
when the first distance is larger than the first preset threshold, determining that the single attendance result to be stored corresponding to each first distance larger than the first preset threshold is determined as not attendance.
Further, after the step of updating the single attendance result library according to each single attendance result to be stored, the method further includes:
acquiring a preset attendance time range and a target attendance staff data set;
acquiring a single attendance result from the single attendance result library according to the target attendance staff data set and the preset attendance time range to obtain a single attendance result set to be calculated;
when the attendance result with the single attendance result in the single attendance result set to be calculated is not attendance, taking each single attendance result with the attendance result being not attendance as a single attendance result set to be analyzed;
sending the single attendance result set to be analyzed to an attendance checking terminal;
acquiring a position data auditing result set sent by the attendance auditing end according to the single attendance result set to be analyzed;
updating the single attendance result library and the single attendance result set to be calculated according to the position data auditing result set;
and performing attendance calculation according to the single attendance result set to be calculated to obtain an employee attendance comprehensive result.
Further, after the step of performing attendance calculation according to the single attendance result set to be calculated to obtain the staff attendance comprehensive result, the method further comprises the following steps of:
acquiring each single attendance result corresponding to the non-empty auditing result from the single attendance result library to serve as a corrected single attendance result set;
and updating the electronic fence generation model according to the corrected single attendance result set.
Further, after the step of performing attendance judgment according to each first distance in the first distance set and the first preset threshold value respectively to obtain the single attendance result to be stored corresponding to each first distance, the method further includes:
acquiring the current time and a preset late arrival reminding time range, and judging whether the current time is in the preset late arrival reminding time range or not;
when the current time is within the preset late-arrival reminding time range, obtaining the single attendance result to be stored which is not on duty from each single attendance result to be stored, and obtaining a single attendance result set to be judged;
acquiring a peripheral electronic fence, and respectively calculating the distance between each employee position data in the single attendance result set to be judged and the boundary of the peripheral electronic fence to obtain a second distance set;
acquiring a second preset threshold, and judging whether a second distance in the second distance set is smaller than or equal to the second preset threshold;
when the second distance is smaller than or equal to the second preset threshold, taking the single attendance result corresponding to each second distance smaller than or equal to the second preset threshold as a single attendance result set to be reminded;
acquiring the single attendance result from the single attendance result set to be reminded, and taking the single attendance result as the single attendance result to be reminded;
calculating the shortest path between the employee position data of the single attendance result to be reminded and the boundary of the target electronic fence to obtain the remaining commuting distance;
acquiring preset staff speed data, and calculating a remaining commuting time set according to the remaining commuting distance and the preset staff speed data;
generating commuting prevention late reminding information according to the employee position data, the remaining commuting distance and the remaining commuting time set of the single attendance result to be reminded;
and sending the commute delay prevention reminding information to a client corresponding to the single attendance result to be reminded.
This application has still provided a staff attendance device based on artificial intelligence, the device includes:
the data acquisition module is used for acquiring a target electronic fence, wherein the target electronic fence is generated by adopting an electronic fence generation model, and the electronic fence generation model is a model obtained based on machine learning;
the employee position data determining module is used for acquiring an employee data set and respectively acquiring employee position data corresponding to each employee data in the employee data set by adopting a preset time interval;
the first distance determining module is used for respectively calculating the distance between the position data of each employee and the boundary of the target electronic fence to obtain a first distance set;
the to-be-stored single attendance checking result determining module is used for acquiring a first preset threshold value, and performing attendance judgment according to each first distance in the first distance set and the first preset threshold value respectively to obtain a to-be-stored single attendance checking result corresponding to each first distance;
and the single attendance result library updating module is used for updating the single attendance result library according to each single attendance result to be stored.
The present application further proposes a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of any of the above methods when executing the computer program.
The present application also proposes a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of any of the above.
The method comprises the steps of firstly obtaining a target electronic fence, wherein the target electronic fence is generated by adopting an electronic fence generation model, the electronic fence generation model is a model obtained based on machine learning, secondly obtaining a staff data set, respectively obtaining staff position data corresponding to each staff data in the staff data set by adopting a preset time interval, then respectively calculating the distance between each staff position data and the boundary of the target electronic fence to obtain a first distance set, and finally obtaining a first preset threshold value, and respectively carrying out attendance judgment according to each first distance in the first distance set and the first preset threshold value to obtain a single attendance result to be stored corresponding to each first distance, the single attendance result library is updated according to each single attendance result to be stored, the attendance result calculation is realized by automatically acquiring employee position data at a preset time interval without requiring the employee to punch the card at a fixed point, and the attendance judgment of the employee can be carried out by acquiring the employee position data next time when the employee leaves the target electronic fence after the employee finishes punching the card and goes out privately, so that the attendance management can be carried out on the employee who goes out privately after the employee finishes punching the card, and the accuracy of the attendance management is improved; and when the staff returns to the target electronic fence, the staff can acquire the position data of the staff next time and judge attendance, so that the problem that the staff is difficult to adopt a card supplementing process to carry out accurate card supplementing when forgetting to charge the card is avoided, and the accuracy of attendance management is improved.
Drawings
Fig. 1 is a schematic flow chart of an employee attendance method based on artificial intelligence according to an embodiment of the present application;
fig. 2 is a block diagram schematically illustrating a structure of an employee attendance device based on artificial intelligence according to an embodiment of the present application;
fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
Referring to fig. 1, an embodiment of the present application provides an employee attendance method based on artificial intelligence, where the method includes:
s1: acquiring a target electronic fence, wherein the target electronic fence is generated by adopting an electronic fence generation model, and the electronic fence generation model is a model obtained based on machine learning;
s2: acquiring a staff data set, and respectively acquiring staff position data corresponding to each staff data in the staff data set by adopting a preset time interval;
s3: respectively calculating the distance between each employee position data and the boundary of the target electronic fence to obtain a first distance set;
s4: acquiring a first preset threshold, and performing attendance judgment according to each first distance in the first distance set and the first preset threshold respectively to obtain a single attendance result to be stored corresponding to each first distance;
s5: and updating the single attendance result library according to each single attendance result to be stored.
In this embodiment, a target electronic fence is obtained first, where the target electronic fence is an electronic fence generated by using an electronic fence generation model, the electronic fence generation model is a model obtained based on machine learning, then a staff data set is obtained, staff position data corresponding to each staff data in the staff data set is obtained respectively at preset time intervals, then distances between each staff position data and a boundary of the target electronic fence are calculated respectively to obtain a first distance set, finally a first preset threshold is obtained, attendance judgment is performed according to each first distance in the first distance set and the first preset threshold respectively to obtain a single attendance result to be stored corresponding to each first distance, and a single attendance result library is updated according to each single attendance result to be stored, the employee position data is automatically acquired at the preset time interval to carry out attendance result calculation under the condition that the employee does not need to punch the card at fixed points, and the employee can be judged to be on duty when the employee leaves the target electronic fence in a private outgoing mode after the employee punches the card, so that the attendance management can be carried out in the private outgoing mode after the employee punches the card, and the accuracy of the attendance management is improved; and when the staff returns to the target electronic fence, the staff can acquire the position data of the staff next time and judge attendance, so that the problem that the staff is difficult to adopt a card supplementing process to carry out accurate card supplementing when forgetting to charge the card is avoided, and the accuracy of attendance management is improved.
For S1, the target electronic fence can be obtained from the database, or can be obtained from a third-party application system.
A target electronic fence, i.e., an electronic fence. The electronic fence is an electronic map boundary.
Optionally, the target electronic fence is an irregularly-shaped electronic fence.
The electronic fence generation model is obtained by training a machine learning model by adopting a plurality of training samples.
For S2, the employee data set may be obtained from a database, may be obtained from a third-party application system, and may also be obtained from the employee data set input by the user.
And the employee data set is a set of employee data of all employees of the office address corresponding to the target electronic fence. One or more employee data are included in the employee data set. Employee data includes, but is not limited to: employee name, employee identification, and employee home address.
It is understood that the employee location data may be obtained from a client of the mobile device, or may be the employee location data actively sent by the client of the mobile device. Mobile devices include, but are not limited to: cell-phone, panel computer, intelligent wearing equipment and worker's card.
Employee location data includes: the position data and the position generation time, wherein the position generation time is the generation time of the position data.
Optionally, the preset time interval is set to 5 seconds.
And acquiring employee position data corresponding to each employee data in the employee data set respectively by adopting a preset time interval, namely, each employee data in the employee data set corresponds to one employee position data.
It can be understood that when the employee data in the employee data set cannot obtain the corresponding employee location data, a preset location acquisition failure identifier may be obtained, and the preset location acquisition failure identifier is used as the employee location data corresponding to the employee data (i.e., the employee data in the employee data set that cannot obtain the employee location data).
For S3, acquiring one employee position data from each employee position data, and taking the acquired employee position data as the employee position data to be calculated; calculating the minimum distance between the position data of the staff to be calculated and the boundary of the target electronic fence to obtain the first distance corresponding to the position data of the staff to be calculated; repeatedly executing the step of acquiring one employee position data from each employee position data and taking the acquired employee position data as the employee position data to be calculated until the acquisition of the employee position data is completed; all the first distances are taken as the first distance set.
For S4, the first preset threshold may also be obtained from the database, the third-party application system may also obtain the first preset threshold, and the first preset threshold may also be written in the program implementing the present application. The first predetermined threshold is a specific value.
And respectively comparing and judging each first distance in the first distance set with the first preset threshold, determining a single attendance result of the first distance according to a comparison and judgment result, and taking the single attendance result as the single attendance result to be stored.
And for S5, updating each single attendance result to be stored to the single attendance result library.
The single attendance result library comprises one or more single attendance results. Single attendance results include, but are not limited to: employee name, employee identification, employee position data, position generation time and attendance result.
In an embodiment, the step of obtaining the target electronic fence includes:
s111: acquiring an electronic fence generating signal, wherein the electronic fence generating signal carries a target office address;
s112: responding to the electronic fence generation signal, and acquiring a data set of attendance staff according to the target office address;
s113: acquiring a staff home address according to the attendance staff data set to obtain a staff home address set to be processed;
s114: vector generation is carried out on the employee home address set to be processed, and address feature vectors to be processed are obtained;
s115: and inputting the address feature vector to be processed into the electronic fence generation model to generate an electronic fence, so as to obtain the target electronic fence.
According to the method and the device, the electronic fence generation is realized by responding to the electronic fence generation signal and performing electronic fence generation according to the employee data set participating in attendance checking, so that the attendance checking accuracy is improved, and the attendance checking management of employee data not participating in attendance checking is reduced.
For S111, an electronic fence generating signal input by the user may be acquired, an electronic fence generating signal sent by the third-party application system may also be acquired, and the electronic fence generating signal actively triggered by the program according to the preset triggering condition may also be implemented. For example, the preset trigger condition is 7 am per day, which is not specifically limited in this example.
The electronic fence generation signal is a signal for generating an electronic fence.
The destination office address is a fixed office address.
And S112, acquiring a data set of the attendance staff according to the target office address.
The attendance staff data set is a set of staff data of staff needing to participate in attendance of the target office address. The attendance staff data set comprises one or more staff data.
And for S113, respectively acquiring the home addresses of the employees from each employee data in the attendance staff data set, and taking the acquired home addresses of the employees as the to-be-processed home address set of the employees.
And S114, generating a coding vector for the to-be-processed employee home address set by adopting an address coding dictionary, and taking the generated coding vector as the to-be-processed address characteristic vector.
The address encoding dictionary includes: address key words and address codes, wherein each address key word corresponds to one address code. Address keys include, but are not limited to: province, city, administrative district, county, street, district.
And generating a coding vector for the employee home address set to be processed, namely converting each address in the employee home address set to be processed into an address code.
For step S115, the address feature vector to be processed is input into the electronic fence generation model to generate an electronic fence, and the generated electronic fence is taken as the target electronic fence.
In one embodiment, before the step of acquiring the target electronic fence, the method further includes:
s121: obtaining a plurality of training samples, the training samples comprising: address sample feature vectors and fence calibrations;
s122: inputting a plurality of training samples into a machine learning model to perform electronic fence generation, and obtaining electronic fence predicted values corresponding to the training samples;
s123: determining a training target according to the difference between the predicted value of the electronic fence and the calibrated value of the electronic fence;
s124: and aiming at the direction of minimizing the value of the training target, adjusting the model parameters of the machine learning model and continuing training until a machine learning end condition is reached, and determining the machine learning model reaching the machine learning end condition as the electronic fence generation model.
According to the electronic fence generation method and device, the electronic fence generation model is obtained by training the machine learning model through the multiple training samples, the accuracy of the generated electronic fence is improved, and therefore a foundation is provided for staff attendance checking based on the electronic fence.
For S121, the address sample feature vector is obtained by mapping each address sample data in the address sample data set into a vector element (that is, an address code), and combining the vector elements obtained by mapping. The set of address sample data includes: and the family address and the work address of the employee are collected. The working address set includes: office address, address of service organization to which work may need to go, address of facilities for staff to and from work routes. Service organizations include, but are not limited to: post office, bank, picture and text store, express delivery shop. Facilities for employee commuting routes include, but are not limited to: overpass, parking area.
Wherein the electronic fence calibration value is an electronic fence manually drawn around a set of work addresses.
For S122, inputting each of the training samples into the machine learning model; outputting, by an output layer of the machine learning model, one fence prediction value for each of the training samples.
Wherein the machine learning model may employ a neural network.
For S123, generating a loss function by taking the electronic fence predicted value and the electronic fence calibration value corresponding to each training sample as independent variables; and carrying out weighted summation on each loss function to obtain the training target.
And the weight for weighting and summing the loss functions is weight data obtained by calibrating the loss functions according to the training samples by a user.
For S124, for the direction of optimizing the training target, adjusting model parameters of an input layer, an intermediate hidden layer, and an output layer of the machine learning model, and continuing training until the machine learning end condition is reached.
And adjusting model parameters of an input layer, a middle hidden layer and an output layer of the machine learning model in a mode of minimizing the training target, and continuing training until the machine learning end condition is reached.
The training target is a global training target, and the process of optimizing the global training target, namely minimizing the loss functions of all samples, and obtaining a global optimal solution is provided.
The machine learning end condition is that the loss value of the machine learning model reaches a first convergence condition or the iteration number reaches a second convergence condition.
The first convergence condition means that the magnitude of the loss values of the machine learning model calculated twice in the neighborhood satisfies a lipschitz condition (lipschitz continuous condition).
The iteration number refers to the number of times that the machine learning model is used for calculating the predicted value of the electronic fence, namely, the iteration number is increased by 1 after one calculation.
The second convergence condition is a specific numerical value.
In an embodiment, the step of performing attendance judgment according to each first distance in the first distance set and the first preset threshold respectively to obtain the single attendance result to be stored corresponding to each first distance includes:
s41: when the first distance is smaller than or equal to the first preset threshold, determining that the single attendance result to be stored corresponding to each first distance smaller than or equal to the first preset threshold is determined as attendance;
s42: when the first distance is larger than the first preset threshold, determining that the single attendance result to be stored corresponding to each first distance larger than the first preset threshold is determined as not attendance.
According to the embodiment, attendance judgment is carried out according to each first distance in the first distance set and the first preset threshold value, so that automatic attendance checking is realized without fixed-point card punching of staff, and the attendance of the staff is monitored in real time.
For S41, when there is a situation that the first distance is smaller than or equal to the first preset threshold, it means that the employee corresponding to each first distance smaller than or equal to the first preset threshold is already in the target electronic fence, and it means attendance in the target electronic fence, so it is determined that the single attendance result to be stored corresponding to each first distance smaller than or equal to the first preset threshold is determined as attendance.
For S42, when there is a first distance greater than the first preset threshold, it means that the employee corresponding to each first distance greater than the first preset threshold is not in the target electronic fence, and does not exist in the target electronic fence, which means that the employee is not attendance, so it is determined that the single attendance result to be stored corresponding to each first distance greater than the first preset threshold is determined as not attendance.
In an embodiment, after the step of updating the single attendance result library according to each single attendance result to be stored, the method further includes:
s61: acquiring a preset attendance time range and a target attendance staff data set;
s62: acquiring a single attendance result from the single attendance result library according to the target attendance staff data set and the preset attendance time range to obtain a single attendance result set to be calculated;
s63: when the attendance result with the single attendance result in the single attendance result set to be calculated is not attendance, taking each single attendance result with the attendance result being not attendance as a single attendance result set to be analyzed;
s64: sending the single attendance result set to be analyzed to an attendance checking terminal;
s65: acquiring a position data auditing result set sent by the attendance auditing end according to the single attendance result set to be analyzed;
s66: updating the single attendance result library and the single attendance result set to be calculated according to the position data auditing result set;
s67: and performing attendance calculation according to the single attendance result set to be calculated to obtain an employee attendance comprehensive result.
The embodiment is based on the single attendance result library, and attendance checking and comprehensive attendance checking are carried out according to the preset attendance time range, so that comprehensive attendance checking is carried out according to the preset attendance time range on the basis of automatic real-time single attendance result, and the accuracy of comprehensive attendance data is improved.
For S61, the preset attendance time range may be obtained from the database, the preset attendance time range input by the user may also be obtained, the preset attendance time range sent by the third-party application system may also be obtained, and the preset attendance time range may also be written into the program implementing the present application.
The preset attendance time range comprises: attendance starting time and attendance ending time. For example, the preset attendance time range is 9:00 to 12:00, where 9:00 is an attendance starting time, and 12:00 is an attendance ending time, which is not specifically limited in this example.
The target attendance staff data set can be obtained from the database, the target attendance staff data set input by the user can also be obtained, and the target attendance staff data set sent by the third-party application system can also be obtained.
The target attendance staff data set is a set of staff data needing to participate in attendance within the preset attendance time range.
For step S62, from the single attendance result library, each single attendance result whose position generation time is within the preset attendance time range and whose employee identifier is located in the target attendance employee data set is taken as the single attendance result set to be calculated. That is to say, the generation time of each position in the to-be-calculated single attendance result set is within the preset attendance time range, and each employee identifier in the to-be-calculated single attendance result set is located in the target attendance staff data set.
For S63, when the attendance result of the single attendance result is not attendance in the single attendance result set to be calculated, it means that the attendance result is not attendance at this time the single attendance result is not attendance as required, and the attendance result is each of the single attendance results that are not attendance as the single attendance result set to be analyzed.
For S64, the single attendance result set to be analyzed is sent to an attendance checking end through communication with the attendance checking end; and the attendance checking end acquires a position data checking result input by a checking person according to the received single attendance result set to be analyzed.
The attendance checking terminal includes but is not limited to: an examination and audit system and an examination and audit module.
And S65, through communication with an attendance checking terminal, acquiring a position data checking result set sent by the attendance checking terminal according to the single attendance result set to be analyzed.
The position data audit result set may include 0 position data audit result, may also include 1 position data audit result, and may also include a plurality of position data audit results. And (5) position data auditing results: employee identification, employee location data, location generation time, and audit results. And the auditing result comprises a normal identifier.
That is, the number of the single attendance results in the location data audit result set is less than or equal to the number of the single attendance results in the single attendance result set to be analyzed.
And S66, according to the single attendance result of the position data audit result set, updating the normal identifier of the position data audit result set to the position data audit result of the single attendance result base and the audit result of the single attendance result set to be calculated.
The single attendance result library comprises: and (4) single attendance checking results and auditing results, wherein each single attendance checking result corresponds to 1 auditing result. The value in the audit result may be a null value or a non-null value.
And S67, according to the single attendance result set to be calculated, performing attendance calculation respectively for the staff corresponding to each staff data in the target attendance staff data set to obtain staff attendance comprehensive results.
The comprehensive result of the attendance of the staff comprises the following steps: staff identification, a preset attendance time range, a normal attendance time range, a non-attendance time range and an attendance comprehensive result. The attendance comprehensive result comprises: normal attendance and abnormal attendance.
In an embodiment, after the step of performing attendance calculation according to the single attendance result set to be calculated to obtain the staff attendance comprehensive result, the method further includes:
s71: acquiring each single attendance result corresponding to the non-empty auditing result from the single attendance result library to serve as a corrected single attendance result set;
s72: and updating the electronic fence generation model according to the corrected single attendance result set.
According to the method and the device, the corrected single attendance result set is determined according to the position data auditing result, and then the corrected single attendance result set is adopted to update the electronic fence generating model, so that the accuracy of the electronic fence generating model is improved, and the attendance accuracy of the method and the device is improved.
And S71, acquiring each single attendance result corresponding to the non-empty auditing result from the single attendance result library, and taking each acquired single attendance result as a corrected single attendance result set. That is, although the attendance result of the corrected single attendance result set is not attendance, the employee position data is already checked to be normal by the attendance checking terminal.
For S72, retraining the fence generation model according to the corrected single attendance result set to implement updating of the fence generation model.
Namely, the position data of each employee in the corrected single attendance result set is used as the address of a service organization which may need to go for work in the work address set, and the training sample is re-determined according to the updated work address set to re-train the electronic fence generation model.
In an embodiment, after the step of performing attendance judgment according to each first distance in the first distance set and the first preset threshold respectively to obtain the single attendance result to be stored corresponding to each first distance, the method further includes:
s81: acquiring the current time and a preset late arrival reminding time range, and judging whether the current time is in the preset late arrival reminding time range or not;
s82: when the current time is within the preset late-arrival reminding time range, obtaining the single attendance result to be stored which is not on duty from each single attendance result to be stored, and obtaining a single attendance result set to be judged;
s83: acquiring a peripheral electronic fence, and respectively calculating the distance between each employee position data in the single attendance result set to be judged and the boundary of the peripheral electronic fence to obtain a second distance set;
s84: acquiring a second preset threshold, and judging whether a second distance in the second distance set is smaller than or equal to the second preset threshold;
s85: when the second distance is smaller than or equal to the second preset threshold, taking the single attendance result corresponding to each second distance smaller than or equal to the second preset threshold as a single attendance result set to be reminded;
s86: acquiring the single attendance result from the single attendance result set to be reminded, and taking the single attendance result as the single attendance result to be reminded;
s87: calculating the shortest path between the employee position data of the single attendance result to be reminded and the boundary of the target electronic fence to obtain the remaining commuting distance;
s88: acquiring preset staff speed data, and calculating a remaining commuting time set according to the remaining commuting distance and the preset staff speed data;
s89: generating commuting prevention late reminding information according to the employee position data, the remaining commuting distance and the remaining commuting time set of the single attendance result to be reminded;
s810: and sending the commute delay prevention reminding information to a client corresponding to the single attendance result to be reminded.
According to the embodiment, the commuting prevention is delayed for reminding according to the preset delay reminding time range and the single attendance result to be stored, so that the staff can adjust the commuting speed in time to prevent delay, and the user experience is improved.
For S81, the world time of the server where the program implementing the present application is located is acquired as the current time.
The preset late-arrival reminding time range can be obtained from the database, the preset late-arrival reminding time range input by a user can also be obtained, the preset late-arrival reminding time range sent by a third-party application system can also be obtained, and the preset late-arrival reminding time range can also be written into a program for realizing the application.
The preset late arrival reminding time range comprises: a reminder start time and a reminder end time. For example, the preset late reminder time range is 8:20 to 8:58, where 8:20 is the reminder start time, and 8:58 is the reminder end time, which is not limited in this example.
When the current time is greater than or equal to a reminding starting time and the current time is less than or equal to a reminding ending time, determining that the current time is within the preset late reminding time range, and otherwise, determining that the current time is not within the preset late reminding time range.
For S82, when the current time is within the preset late arrival reminding time range, obtaining the single attendance result to be stored from each single attendance result to be stored, wherein the attendance result is the single attendance result to be stored which is not on attendance, and taking each obtained single attendance result to be stored as the single attendance result set to be judged.
For S83, the peripheral electronic fence can be obtained from the database, or can be obtained from a third-party application system.
The peripheral electronic fence is an electronic fence generated according to the target electronic fence, and the area of the peripheral electronic fence is larger than that of the target electronic fence.
And respectively calculating the minimum distance between each employee position data in the single attendance result set to be judged and the boundary of the peripheral electronic fence, and taking each calculated minimum distance as the second distance set. That is, the second distance in the second set of distances is the minimum distance of the employee location data from the boundary of the peripheral electronic fence.
For S84, the second preset threshold may be obtained from the database, or the second preset threshold input by the user may be obtained, or the second preset threshold sent by the third-party application system may be obtained, or the second preset threshold may be written in the program implementing the present application. The second predetermined threshold is a specific value.
For S85, when there is a second distance that is less than or equal to the second preset threshold, the staff corresponding to the second distance that is less than or equal to the second preset threshold is not attendance and is already located between the peripheral electronic fence and the target electronic fence, and it is necessary to perform commute prevention late reminding on these staff, so that the single attendance result corresponding to each second distance that is less than or equal to the second preset threshold is taken as a single attendance result set to be reminded.
When the second distance is larger than the second preset threshold value, the staff corresponding to the second distance larger than the second preset threshold value can arrive late even if the commuting speed is adjusted due to the fact that the distance is too far, and therefore the necessity of commuting prevention late reminding is avoided.
And S86, acquiring one single attendance result from the single attendance result set to be reminded, and taking the acquired single attendance result as the single attendance result to be reminded.
For S87, performing path planning according to the employee position data of the single attendance result to be reminded and the target electronic fence by adopting a path planning algorithm to obtain a path set; finding out the path with the shortest length from the path set to obtain the shortest path; and taking the length of the shortest path as the remaining commuting distance.
For S88, the preset employee speed data may be obtained from the database, or the preset employee speed data sent by the third-party application system may be obtained, or the preset employee speed data may be written in the program implementing the present application.
The preset employee speed data includes: commute mode and commute speed. Commuting modes include, but are not limited to: walking, cycling, motorcycling, automobiles, public transportation.
And dividing the remaining commuting distance by each commuting speed in the preset staff speed data to obtain a remaining commuting time length set.
The set of remaining commute durations includes: the commute mode and the remaining commute duration.
And for S89, a preset reminding information generation template is adopted, and the commuting prevention late arrival reminding information is generated according to the employee position data, the remaining commuting distance and the remaining commuting time set of the single attendance result to be reminded.
The commute prevention late reminding information comprises: the employee location data, the remaining commute distance, and the remaining commute duration set.
And S810, sending the commute delay prevention reminding information to the client of the mobile equipment of the staff corresponding to the single attendance result to be reminded, thereby realizing the delay prevention reminding of the staff.
Referring to fig. 2, the present application further provides an employee attendance device based on artificial intelligence, the device includes:
the data acquisition module 100 is configured to acquire a target electronic fence, where the target electronic fence is an electronic fence generated by using an electronic fence generation model, and the electronic fence generation model is a model obtained based on machine learning;
the employee position data determining module 200 is configured to acquire an employee data set, and acquire employee position data corresponding to each employee data in the employee data set, respectively, at preset time intervals;
a first distance determining module 300, configured to calculate a distance between each of the employee location data and a boundary of the target electronic fence, respectively, to obtain a first distance set;
a to-be-stored single attendance result determining module 400, configured to obtain a first preset threshold, and perform attendance judgment according to each first distance in the first distance set and the first preset threshold, respectively, to obtain a to-be-stored single attendance result corresponding to each first distance;
and the single attendance result library updating module 500 is used for updating the single attendance result library according to each single attendance result to be stored.
In this embodiment, a target electronic fence is obtained first, where the target electronic fence is an electronic fence generated by using an electronic fence generation model, the electronic fence generation model is a model obtained based on machine learning, then a staff data set is obtained, staff position data corresponding to each staff data in the staff data set is obtained respectively at preset time intervals, then distances between each staff position data and a boundary of the target electronic fence are calculated respectively to obtain a first distance set, finally a first preset threshold is obtained, attendance judgment is performed according to each first distance in the first distance set and the first preset threshold respectively to obtain a single attendance result to be stored corresponding to each first distance, and a single attendance result library is updated according to each single attendance result to be stored, the employee position data is automatically acquired at the preset time interval to carry out attendance result calculation under the condition that the employee does not need to punch the card at fixed points, and the employee can be judged to be on duty when the employee leaves the target electronic fence in a private outgoing mode after the employee punches the card, so that the attendance management can be carried out in the private outgoing mode after the employee punches the card, and the accuracy of the attendance management is improved; and when the staff returns to the target electronic fence, the staff can acquire the position data of the staff next time and judge attendance, so that the problem that the staff is difficult to adopt a card supplementing process to carry out accurate card supplementing when forgetting to charge the card is avoided, and the accuracy of attendance management is improved.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer equipment is used for storing data such as employee attendance checking methods based on artificial intelligence. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by the processor to realize an artificial intelligence-based employee attendance method. The employee attendance method based on artificial intelligence comprises the following steps: acquiring a target electronic fence, wherein the target electronic fence is generated by adopting an electronic fence generation model, and the electronic fence generation model is a model obtained based on machine learning; acquiring a staff data set, and respectively acquiring staff position data corresponding to each staff data in the staff data set by adopting a preset time interval; respectively calculating the distance between each employee position data and the boundary of the target electronic fence to obtain a first distance set; acquiring a first preset threshold, and performing attendance judgment according to each first distance in the first distance set and the first preset threshold respectively to obtain a single attendance result to be stored corresponding to each first distance; and updating the single attendance result library according to each single attendance result to be stored.
In this embodiment, a target electronic fence is obtained first, where the target electronic fence is an electronic fence generated by using an electronic fence generation model, the electronic fence generation model is a model obtained based on machine learning, then a staff data set is obtained, staff position data corresponding to each staff data in the staff data set is obtained respectively at preset time intervals, then distances between each staff position data and a boundary of the target electronic fence are calculated respectively to obtain a first distance set, finally a first preset threshold is obtained, attendance judgment is performed according to each first distance in the first distance set and the first preset threshold respectively to obtain a single attendance result to be stored corresponding to each first distance, and a single attendance result library is updated according to each single attendance result to be stored, the employee position data is automatically acquired at the preset time interval to carry out attendance result calculation under the condition that the employee does not need to punch the card at fixed points, and the employee can be judged to be on duty when the employee leaves the target electronic fence in a private outgoing mode after the employee punches the card, so that the attendance management can be carried out in the private outgoing mode after the employee punches the card, and the accuracy of the attendance management is improved; and when the staff returns to the target electronic fence, the staff can acquire the position data of the staff next time and judge attendance, so that the problem that the staff is difficult to adopt a card supplementing process to carry out accurate card supplementing when forgetting to charge the card is avoided, and the accuracy of attendance management is improved.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements an employee attendance method based on artificial intelligence, and the method includes the steps of: acquiring a target electronic fence, wherein the target electronic fence is generated by adopting an electronic fence generation model, and the electronic fence generation model is a model obtained based on machine learning; acquiring a staff data set, and respectively acquiring staff position data corresponding to each staff data in the staff data set by adopting a preset time interval; respectively calculating the distance between each employee position data and the boundary of the target electronic fence to obtain a first distance set; acquiring a first preset threshold, and performing attendance judgment according to each first distance in the first distance set and the first preset threshold respectively to obtain a single attendance result to be stored corresponding to each first distance; and updating the single attendance result library according to each single attendance result to be stored.
The staff attendance method based on artificial intelligence comprises the steps of firstly obtaining a target electronic fence, wherein the target electronic fence is generated by adopting an electronic fence generation model, the electronic fence generation model is a model obtained based on machine learning, secondly obtaining a staff data set, respectively obtaining staff position data corresponding to each staff data in the staff data set by adopting a preset time interval, then respectively calculating the distance between each staff position data and the boundary of the target electronic fence to obtain a first distance set, finally obtaining a first preset threshold, respectively carrying out attendance judgment according to each first distance in the first distance set and the first preset threshold to obtain single attendance results to be stored corresponding to each first distance, and updating a single attendance result library according to each single attendance result to be stored, the employee position data is automatically acquired at the preset time interval to carry out attendance result calculation under the condition that the employee does not need to punch the card at fixed points, and the employee can be judged to be on duty when the employee leaves the target electronic fence in a private outgoing mode after the employee punches the card, so that the attendance management can be carried out in the private outgoing mode after the employee punches the card, and the accuracy of the attendance management is improved; and when the staff returns to the target electronic fence, the staff can acquire the position data of the staff next time and judge attendance, so that the problem that the staff is difficult to adopt a card supplementing process to carry out accurate card supplementing when forgetting to charge the card is avoided, and the accuracy of attendance management is improved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (10)
1. An employee attendance method based on artificial intelligence is characterized by comprising the following steps:
acquiring a target electronic fence, wherein the target electronic fence is generated by adopting an electronic fence generation model, and the electronic fence generation model is a model obtained based on machine learning;
acquiring a staff data set, and respectively acquiring staff position data corresponding to each staff data in the staff data set by adopting a preset time interval;
respectively calculating the distance between each employee position data and the boundary of the target electronic fence to obtain a first distance set;
acquiring a first preset threshold, and performing attendance judgment according to each first distance in the first distance set and the first preset threshold respectively to obtain a single attendance result to be stored corresponding to each first distance;
and updating the single attendance result library according to each single attendance result to be stored.
2. The artificial intelligence based employee attendance method according to claim 1 wherein the step of obtaining a target electronic fence comprises:
acquiring an electronic fence generating signal, wherein the electronic fence generating signal carries a target office address;
responding to the electronic fence generation signal, and acquiring a data set of attendance staff according to the target office address;
acquiring a staff home address according to the attendance staff data set to obtain a staff home address set to be processed;
vector generation is carried out on the employee home address set to be processed, and address feature vectors to be processed are obtained;
and inputting the address feature vector to be processed into the electronic fence generation model to generate an electronic fence, so as to obtain the target electronic fence.
3. The artificial intelligence based employee attendance method as claimed in claim 1, wherein the step of obtaining the target electronic fence is preceded by the further steps of:
obtaining a plurality of training samples, the training samples comprising: address sample feature vectors and fence calibrations;
inputting a plurality of training samples into a machine learning model to perform electronic fence generation, and obtaining electronic fence predicted values corresponding to the training samples;
determining a training target according to the difference between the predicted value of the electronic fence and the calibrated value of the electronic fence;
and aiming at the direction of minimizing the value of the training target, adjusting the model parameters of the machine learning model and continuing training until a machine learning end condition is reached, and determining the machine learning model reaching the machine learning end condition as the electronic fence generation model.
4. The employee attendance method based on artificial intelligence according to claim 1, wherein the step of performing attendance judgment according to each first distance in the first distance set and the first preset threshold value to obtain a single attendance result to be stored corresponding to each first distance includes:
when the first distance is smaller than or equal to the first preset threshold, determining that the single attendance result to be stored corresponding to each first distance smaller than or equal to the first preset threshold is determined as attendance;
when the first distance is larger than the first preset threshold, determining that the single attendance result to be stored corresponding to each first distance larger than the first preset threshold is determined as not attendance.
5. The artificial intelligence based employee attendance method according to claim 1, wherein after the step of updating the single attendance result repository in accordance with the respective single attendance result to be stored, further comprising:
acquiring a preset attendance time range and a target attendance staff data set;
acquiring a single attendance result from the single attendance result library according to the target attendance staff data set and the preset attendance time range to obtain a single attendance result set to be calculated;
when the attendance result with the single attendance result in the single attendance result set to be calculated is not attendance, taking each single attendance result with the attendance result being not attendance as a single attendance result set to be analyzed;
sending the single attendance result set to be analyzed to an attendance checking terminal;
acquiring a position data auditing result set sent by the attendance auditing end according to the single attendance result set to be analyzed;
updating the single attendance result library and the single attendance result set to be calculated according to the position data auditing result set;
and performing attendance calculation according to the single attendance result set to be calculated to obtain an employee attendance comprehensive result.
6. The artificial intelligence based employee attendance method according to claim 5, wherein after the step of performing attendance calculation according to the single attendance result set to be calculated to obtain the employee attendance comprehensive result, the method further comprises:
acquiring each single attendance result corresponding to the non-empty auditing result from the single attendance result library to serve as a corrected single attendance result set;
and updating the electronic fence generation model according to the corrected single attendance result set.
7. The employee attendance method based on artificial intelligence according to claim 1, wherein after the step of performing attendance judgment according to each first distance in the first distance set and the first preset threshold value respectively to obtain the single attendance result to be stored corresponding to each first distance, the method further comprises:
acquiring the current time and a preset late arrival reminding time range, and judging whether the current time is in the preset late arrival reminding time range or not;
when the current time is within the preset late-arrival reminding time range, obtaining the single attendance result to be stored which is not on duty from each single attendance result to be stored, and obtaining a single attendance result set to be judged;
acquiring a peripheral electronic fence, and respectively calculating the distance between each employee position data in the single attendance result set to be judged and the boundary of the peripheral electronic fence to obtain a second distance set;
acquiring a second preset threshold, and judging whether a second distance in the second distance set is smaller than or equal to the second preset threshold;
when the second distance is smaller than or equal to the second preset threshold, taking the single attendance result corresponding to each second distance smaller than or equal to the second preset threshold as a single attendance result set to be reminded;
acquiring the single attendance result from the single attendance result set to be reminded, and taking the single attendance result as the single attendance result to be reminded;
calculating the shortest path between the employee position data of the single attendance result to be reminded and the boundary of the target electronic fence to obtain the remaining commuting distance;
acquiring preset staff speed data, and calculating a remaining commuting time set according to the remaining commuting distance and the preset staff speed data;
generating commuting prevention late reminding information according to the employee position data, the remaining commuting distance and the remaining commuting time set of the single attendance result to be reminded;
and sending the commute delay prevention reminding information to a client corresponding to the single attendance result to be reminded.
8. An employee attendance device based on artificial intelligence, the device comprising:
the data acquisition module is used for acquiring a target electronic fence, wherein the target electronic fence is generated by adopting an electronic fence generation model, and the electronic fence generation model is a model obtained based on machine learning;
the employee position data determining module is used for acquiring an employee data set and respectively acquiring employee position data corresponding to each employee data in the employee data set by adopting a preset time interval;
the first distance determining module is used for respectively calculating the distance between the position data of each employee and the boundary of the target electronic fence to obtain a first distance set;
the to-be-stored single attendance checking result determining module is used for acquiring a first preset threshold value, and performing attendance judgment according to each first distance in the first distance set and the first preset threshold value respectively to obtain a to-be-stored single attendance checking result corresponding to each first distance;
and the single attendance result library updating module is used for updating the single attendance result library according to each single attendance result to be stored.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110874816.7A CN113642984A (en) | 2021-07-30 | 2021-07-30 | Employee attendance checking method, device, equipment and storage medium based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110874816.7A CN113642984A (en) | 2021-07-30 | 2021-07-30 | Employee attendance checking method, device, equipment and storage medium based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113642984A true CN113642984A (en) | 2021-11-12 |
Family
ID=78419154
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110874816.7A Pending CN113642984A (en) | 2021-07-30 | 2021-07-30 | Employee attendance checking method, device, equipment and storage medium based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642984A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115273265A (en) * | 2022-09-22 | 2022-11-01 | 山东云小兵信息技术有限公司 | Intelligent card punching reminding method, system, device and readable storage medium |
| CN116503968A (en) * | 2023-06-28 | 2023-07-28 | 南方电网调峰调频发电有限公司信息通信分公司 | Remote punching method and device for power generation enterprises |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150141045A1 (en) * | 2013-11-21 | 2015-05-21 | Telecommunication Systems, Inc. | Geofence |
| CN108053510A (en) * | 2017-12-26 | 2018-05-18 | 苏州达家迎信息技术有限公司 | Intelligent attendance system and method |
| CN108711199A (en) * | 2018-05-10 | 2018-10-26 | 成都精位科技有限公司 | Automatic punch card method, device, electronic equipment and readable storage medium storing program for executing |
| CN109146406A (en) * | 2018-07-24 | 2019-01-04 | 数海信息技术有限公司 | Number Hisense based on GPS positioning information auxiliary RFID technique ceases attendance checking system |
| CN109583824A (en) * | 2017-09-29 | 2019-04-05 | 腾讯科技（深圳）有限公司 | A kind of Work attendance method, system, equipment and computer readable storage medium |
| CN109754482A (en) * | 2019-01-28 | 2019-05-14 | 深圳壹账通智能科技有限公司 | Automatically method, apparatus, computer equipment and the storage medium checked card |
| CN109829994A (en) * | 2018-12-13 | 2019-05-31 | 平安万家医疗投资管理有限责任公司 | A kind of Work attendance method, device, computer equipment and readable storage medium storing program for executing |
| CN111190980A (en) * | 2019-12-23 | 2020-05-22 | 中移（杭州）信息技术有限公司 | Late arrival early warning method and device, electronic equipment and storage medium |
| CN111784862A (en) * | 2020-08-09 | 2020-10-16 | 泉州征之魂智能科技服务有限公司 | Automatic attendance checking method based on mobile terminal |
| CN111798584A (en) * | 2020-08-09 | 2020-10-20 | 泉州征之魂智能科技服务有限公司 | Remote automatic attendance checking method based on mobile terminal |
| US20200344567A1 (en) * | 2019-04-29 | 2020-10-29 | Here Global B.V. | Geofence prioritization |
| CN111898995A (en) * | 2020-08-07 | 2020-11-06 | 工银科技有限公司 | Attendance checking method, device and system |
| KR20200134034A (en) * | 2019-05-21 | 2020-12-01 | 이호진 | Method and system for accident prevention and attendance management in the workplace |
| CN112311824A (en) * | 2019-07-29 | 2021-02-02 | 腾讯科技（深圳）有限公司 | Attendance information processing method and related device |
| CN112991569A (en) * | 2021-02-23 | 2021-06-18 | 上海慧贤网络科技有限公司 | Attendance card punching method and related device |
-
2021
- 2021-07-30 CN CN202110874816.7A patent/CN113642984A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150141045A1 (en) * | 2013-11-21 | 2015-05-21 | Telecommunication Systems, Inc. | Geofence |
| CN109583824A (en) * | 2017-09-29 | 2019-04-05 | 腾讯科技（深圳）有限公司 | A kind of Work attendance method, system, equipment and computer readable storage medium |
| CN108053510A (en) * | 2017-12-26 | 2018-05-18 | 苏州达家迎信息技术有限公司 | Intelligent attendance system and method |
| CN108711199A (en) * | 2018-05-10 | 2018-10-26 | 成都精位科技有限公司 | Automatic punch card method, device, electronic equipment and readable storage medium storing program for executing |
| CN109146406A (en) * | 2018-07-24 | 2019-01-04 | 数海信息技术有限公司 | Number Hisense based on GPS positioning information auxiliary RFID technique ceases attendance checking system |
| CN109829994A (en) * | 2018-12-13 | 2019-05-31 | 平安万家医疗投资管理有限责任公司 | A kind of Work attendance method, device, computer equipment and readable storage medium storing program for executing |
| CN109754482A (en) * | 2019-01-28 | 2019-05-14 | 深圳壹账通智能科技有限公司 | Automatically method, apparatus, computer equipment and the storage medium checked card |
| US20200344567A1 (en) * | 2019-04-29 | 2020-10-29 | Here Global B.V. | Geofence prioritization |
| KR20200134034A (en) * | 2019-05-21 | 2020-12-01 | 이호진 | Method and system for accident prevention and attendance management in the workplace |
| CN112311824A (en) * | 2019-07-29 | 2021-02-02 | 腾讯科技（深圳）有限公司 | Attendance information processing method and related device |
| CN111190980A (en) * | 2019-12-23 | 2020-05-22 | 中移（杭州）信息技术有限公司 | Late arrival early warning method and device, electronic equipment and storage medium |
| CN111898995A (en) * | 2020-08-07 | 2020-11-06 | 工银科技有限公司 | Attendance checking method, device and system |
| CN111784862A (en) * | 2020-08-09 | 2020-10-16 | 泉州征之魂智能科技服务有限公司 | Automatic attendance checking method based on mobile terminal |
| CN111798584A (en) * | 2020-08-09 | 2020-10-20 | 泉州征之魂智能科技服务有限公司 | Remote automatic attendance checking method based on mobile terminal |
| CN112991569A (en) * | 2021-02-23 | 2021-06-18 | 上海慧贤网络科技有限公司 | Attendance card punching method and related device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115273265A (en) * | 2022-09-22 | 2022-11-01 | 山东云小兵信息技术有限公司 | Intelligent card punching reminding method, system, device and readable storage medium |
| CN116503968A (en) * | 2023-06-28 | 2023-07-28 | 南方电网调峰调频发电有限公司信息通信分公司 | Remote punching method and device for power generation enterprises |
| CN116503968B (en) * | 2023-06-28 | 2024-01-02 | 南方电网调峰调频发电有限公司信息通信分公司 | Remote punching method and device for power generation enterprises |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113642984A (en) | Employee attendance checking method, device, equipment and storage medium based on artificial intelligence | |
| CN112417273B (en) | Region portrait image generation method, region portrait image generation device, computer equipment and storage medium | |
| JP2016536597A (en) | Method for predicting destination while moving | |
| CN112419710B (en) | Traffic congestion data prediction method, traffic congestion data prediction device, computer equipment and storage medium | |
| CN111897673A (en) | Operation and maintenance fault root cause identification method and device, computer equipment and storage medium | |
| CN112256825A (en) | Medical field multi-turn dialogue intelligent question-answering method and device and computer equipment | |
| CN108038544B (en) | Neural network deep learning method and system based on big data and deep learning | |
| JP2017215898A (en) | Machine learning system | |
| CN111598213B (en) | Network training method, data identification method, device, equipment and medium | |
| CN113792682A (en) | Human face quality evaluation method, device, equipment and medium based on human face image | |
| CN111901554B (en) | Call channel construction method and device based on semantic clustering and computer equipment | |
| CN111831908A (en) | Medical field knowledge graph construction method, device, equipment and storage medium | |
| CN111626519A (en) | Flight arrival time prediction method and device and electronic equipment | |
| CN111178714A (en) | Intimacy degree determination method and device, computer equipment and storage medium | |
| CN114819135A (en) | Training method of detection model, target detection method, device and storage medium | |
| CN113642707A (en) | Model training method, device, equipment and storage medium based on federal learning | |
| CN113204619B (en) | Sentence completion method, device, equipment and medium based on natural language processing | |
| CN114360522A (en) | Training method of voice awakening model, and detection method and equipment of voice false awakening | |
| CN113643046A (en) | Common situation strategy recommendation method, device, equipment and medium suitable for virtual reality | |
| CN110232108B (en) | Man-machine conversation method and conversation system | |
| CN115297437B (en) | Positioning sign-in method, system, equipment and medium applied to positioning watch | |
| CN111899765A (en) | Method and device for sending voice based on emotion prediction model and computer equipment | |
| CN113919953A (en) | Method, device, equipment and storage medium for realizing cross-chain generation of intelligent contract | |
| CN113312481A (en) | Text classification method, device and equipment based on block chain and storage medium | |
| CN114331266A (en) | Recommendation model training method and device and loading and unloading point recommendation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |