CN114298489A - Intelligent monitoring method and system for different catering kitchens and storage medium - Google Patents
Intelligent monitoring method and system for different catering kitchens and storage medium Download PDFInfo
- Publication number
- CN114298489A CN114298489A CN202111488628.7A CN202111488628A CN114298489A CN 114298489 A CN114298489 A CN 114298489A CN 202111488628 A CN202111488628 A CN 202111488628A CN 114298489 A CN114298489 A CN 114298489A
- Authority
- CN
- China
- Prior art keywords
- target
- acquisition
- violation
- targets
- weight
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000012806 monitoring device Methods 0.000 claims abstract description 7
- 238000013139 quantization Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000012797 qualification Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 6
- 239000002699 waste material Substances 0.000 abstract description 5
- 230000001276 controlling effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides an intelligent monitoring method, a system and a storage medium for different catering kitchens, which comprises the following steps: collecting target related data information, generating an index set after quantization processing, and calculating the rating score of the target based on the index set; based on the total single-day acquisition time of all the targets and the rating scores of all the targets, performing acquisition time timing on all the targets, dividing the total single-day acquisition time and giving weight to each time period; obtaining the acquisition sequence of each target based on the reverse alignment of the rating score and the weight; sequentially controlling the field monitoring devices of all targets according to the acquisition sequence and the timing to acquire video streams according to the acquisition timing; and carrying out violation identification on the image frames in the acquired video stream based on a preset identification model. The invention can greatly reduce the investment of supervision personnel, and solves the problems that the resource waste can occur and the relative cost is higher when the same management technology is adopted for supervision aiming at different catering units in the existing method.
Description
Technical Field
The invention relates to the technical field of food safety supervision, in particular to an intelligent monitoring method, system and storage medium for different food kitchens.
Background
The conventional intelligent monitoring method for the kitchen of the catering department monitors the kitchen of the catering department through video cameras, and the implementation of the technical method has certain challenges due to the large number of the video cameras. At present, catering units are different in scale, management levels are different, and the incidence rate of kitchen violation problems is different greatly.
Disclosure of Invention
The invention aims to provide an intelligent monitoring method, an intelligent monitoring system and a storage medium for different catering kitchens, and aims to solve the problems that in the background art, the situation of resource waste and relative high cost are caused by adopting the same management technology for supervision of different catering units.
The embodiment of the invention is realized by the following technical scheme: an intelligent monitoring method for different catering kitchens comprises the following steps:
collecting target related data information, generating an index set through quantization processing, and calculating a rating score of a target based on the index set, wherein the data information comprises target basic information, qualification permission information, negative information and administrative penalty information;
on the basis of the total single-day acquisition duration of all the targets and the rating scores of all the targets, carrying out time duration timing on the acquisition of all the targets, dividing the total single-day acquisition duration and giving a weight to each time period, wherein the weight is determined according to the violation condition of each target;
carrying out reverse alignment on the maximum value of the rating score and the minimum value of the weight to obtain the acquisition sequence of each target;
sequentially controlling the on-site monitoring devices of all targets to acquire video streams according to the acquired acquisition sequence and the acquisition time duration;
and carrying out violation identification on the image frames in the acquired video stream based on a preset identification model.
Further, the collecting target related data information and generating an index set through quantization processing includes:
collecting target scale size, grade, duration, number of employees, complaint information, permission information, and administrative penalty information;
and generating an index set by a frequency statistics or segmentation assignment mode.
Further, the calculating a rank score of the target based on the index set further comprises:
the index set is normalized according to the following formula:
in the above formula, XnIndicates the nth index, mu, in the index setnMeans, σ, representing the n-th index of the setnIndicating the standard deviation of the nth index in the set of indices.
Further, the expression of calculating the rank score of the target based on the index set is as follows:
in the above formula, SmRepresents the m-th target rating score, the higher the score, the better the grade, betanAnd b represents the intercept term.
Further, the expression of the time distribution of the collection duration of each target based on the total collection duration of each day of all the targets and the rating scores of each target is as follows:
in the above formula, tmRepresenting the acquisition time timing of the mth target, t representing the total acquisition time per day of all targets, OmRepresents the floating acquisition time, S, of the mth targetiIndicating the rank score of the ith target.
Further, the preset recognition model is obtained by adopting the following method:
randomly acquiring image frames from video streams of all targets, and constructing a sample set by carrying out violation type marking on the image frames;
taking a sample set as input, training by adopting a deep learning algorithm YOLOv3, and generating a recognition model, wherein the output result of the recognition model comprises violation probability and violation type, and the violation probability is determined by a violation probability threshold.
Further, after the violation identification is performed on the image frames in the captured video stream based on the preset identification model, the method further includes:
updating the weight of each time period in the acquisition sequence based on the violation identification result output by the identification model, wherein the formula is as follows:
in the above formula, ωmWeight, g, representing the m-th time periodmRepresenting the number of violations in the m-th time slot in the violation identification result, giRepresenting the number of violations of the ith time slot in the violation identification result;
and updating the rating scores of all the targets based on the violation identification result output by the identification model, wherein the formula is as follows:
in the above formula, a and b are harmonic coefficients, z is the number of frames in the video stream corresponding to the mth target, k is the number of violations in the video stream corresponding to the mth target,
the violation type at the jth violation coordinate of the ith image frame in the video stream is lijCoefficient of time expansion, PijThe probability of violation at the jth violation coordinate of the ith image frame is obtained;
the collection order is updated based on the updated weights and the rank scores.
The invention also provides an intelligent monitoring system for different catering kitchens, which is applied to the method and comprises the following steps:
the system comprises a rating score calculation module, a rating score calculation module and a rating score calculation module, wherein the rating score calculation module is used for collecting target related data information, generating an index set through quantitative processing, and calculating a rating score of a target based on the index set, and the data information comprises target basic information, qualification permission information, negative information and administrative penalty information;
the acquisition module of the acquisition duration and weight, is used for on the basis of the total acquisition duration of single day and rank score of every goal of all goals, set time to the acquisition duration of every goal, and divide the total acquisition duration of said single day and assign the weight to every time quantum, the said weight is confirmed according to the violation situation of each goal;
the acquisition sequence acquisition module is used for carrying out reverse alignment on the maximum value of the rating score and the minimum value of the weight to obtain the acquisition sequence of each target;
the video stream acquisition module is used for controlling the on-site monitoring device of each target in sequence according to the acquired acquisition sequence and the acquisition time duration to acquire video streams according to the acquisition time duration;
and the violation identification module is used for carrying out violation identification on the image frames in the acquired video stream based on a preset identification model.
The present invention also provides an electronic device comprising:
a memory storing execution instructions; and
a processor executing execution instructions stored by the memory to cause the processor to perform the method as described above.
The invention also provides a readable storage medium having stored therein execution instructions, which when executed by a processor, are adapted to implement the method as described above.
The technical scheme of the embodiment of the invention at least has the following advantages and beneficial effects: according to the intelligent monitoring method for different catering kitchens, provided by the invention, the targets are scored according to the scale, the management level, the incidence rate of kitchen violation problems and the like of each catering unit, in addition, the time for acquiring the duration of a single day is timed, the total acquisition duration is divided and respectively given with weights, and the acquisition sequence is obtained based on the scores and the weights, so that different targets are hierarchically supervised according to the sequence and the corresponding acquisition duration, the investment of supervision personnel can be greatly reduced, and the problems that the resource waste condition occurs and the relative cost is higher when the supervision is performed by adopting the same management technology for different catering units in the existing method are solved;
according to the intelligent monitoring method for different catering kitchens, the violation identification result is analyzed to obtain the near condition of the target, the weight and the score of the violation identification result are updated, the acquisition sequence is determined again, appropriate supervision resources can be distributed to the target in real time, and the supervision accuracy is improved.
Drawings
Fig. 1 is a schematic flow chart of an intelligent monitoring method provided in embodiment 1 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Example 1
The research of the applicant finds that the existing intelligent monitoring method for the kitchen of the catering department supervises the kitchen of the catering department through the video cameras, and the implementation of the technical method has certain challenges due to the large number of the video cameras. At present, catering units are different in scale and management level, the incidence rate of kitchen violation problems is different greatly, if the same management technology is adopted for supervision, the resource waste situation can occur, and the relative cost is higher. In view of the above problems, embodiments of the present invention provide an intelligent monitoring method, system and storage medium for different catering kitchens, which aim to solve the problems that resources are wasted and the relative cost is high when different catering units adopt the same management technology for supervision. Referring to fig. 1, the specific steps are as follows:
collecting target-related data information, wherein the data information comprises target basic information, asset licensing information, negative information and administrative penalty information; the embodiment specifically includes: scale size, grade, duration, number of employees, complaint information, licensing information, and administrative penalty information; and generating an index set by quantitative processing modes such as frequency statistics or segmented assignment, such as (X)1， X2，X3，...Xn)。
Further, after the index set is obtained, the index set is normalized, and the formula is expressed as:
in the above formula, XnIndicates the nth index, mu, in the index setnMeans, σ, representing the n-th index of the setnIndicating the standard deviation of the nth index in the set of indices.
The target rank score is then calculated according to the following expression:
in the above formula, SmRepresents the m-th target rating score, the higher the score, the better the grade, betanAnd b represents the intercept term.
Further, based on the total single-day collection duration of all the targets and the rating scores of the targets, when the collection duration of each target is matched, the expression is as follows:
in the above formula, tmRepresenting the acquisition time timing of the mth target, t representing the total acquisition time per day of all targets, OmRepresenting the floating acquisition time of the mth target, which parameter is primarily intended to guarantee regulatory flexibility, OmIf greater than 0, t is increased by the corresponding duration, SiIndicating the rank score of the ith target.
Further, dividing the total single-day acquisition time into m parts, and giving a weight W to each time periodt＝(ω1,ω2,...,ωm),0<＝ωm<1, determining the weight according to the violation condition of each target; if the acquisition is the first acquisition, the weight is a random number. Reverse-aligning the maximum of the rank score with the minimum of the weight, i.e., ωmThe position is not moved, and the larger S ismWith smaller omegamAligning the positions to obtain the acquisition sequence of each target, namely SmThe order of the positions of (a).
And sequentially controlling the field monitoring devices of all targets to acquire video streams according to the acquired acquisition sequence and the acquisition time duration, recording corresponding acquisition time, storing an acquisition result to an address A, and ending acquisition until t time.
Further, carrying out violation identification on the image frames in the collected video stream based on a preset identification model; the preset recognition model of this embodiment is obtained as follows: randomly acquiring image frames from video streams of all targets, and carrying out violation type labeling processing on the image frames by using Label to construct a sample set; taking a sample set as input, training by adopting a deep learning algorithm YOLOv3, generating a recognition model, wherein the output result of the recognition model comprises violation probability and violation type, the violation probability is determined by a violation probability threshold, and the output result is stored to an address B. According to the embodiment of the invention, different targets are supervised in a grading manner according to the sequence and the corresponding acquisition duration, so that the investment of supervision personnel can be greatly reduced, and the problems that the resource waste situation occurs and the relative cost is high due to the fact that the supervision is carried out by adopting the same management technology aiming at different catering units in the existing method are solved.
In addition, after the operation of one cycle, the weight of each time period in the acquisition sequence is updated based on the violation identification result output by the identification model, and the formula is as follows:
in the above formula, ωmWeight, g, representing the m-th time periodmRepresenting the number of violations in the m-th time slot in the violation identification result, giRepresenting the number of violations of the ith time slot in the violation identification result;
and updating the rating scores of all the targets based on the violation identification result output by the identification model, wherein the formula is as follows:
in the above formula, a and b are harmonic coefficients, z is the number of frames in the video stream corresponding to the mth target, k is the number of violations in the video stream corresponding to the mth target,
the violation type at the jth violation coordinate of the ith image frame in the video stream is lijCoefficient of time expansion, PijThe probability of violation at the jth violation coordinate of the ith image frame is obtained; the collection order is updated based on the updated weights and the rank scores. According to the embodiment of the invention, proper supervision resources can be distributed to the target in real time by re-determining the acquisition sequence, and the supervision accuracy is improved.
The embodiment of the invention also provides an intelligent monitoring system for different catering kitchens, which is applied to the method and comprises the following steps:
the system comprises a rating score calculation module, a rating score calculation module and a rating score calculation module, wherein the rating score calculation module is used for collecting target related data information, generating an index set through quantitative processing, and calculating a rating score of a target based on the index set, and the data information comprises target basic information, qualification permission information, negative information and administrative penalty information;
the acquisition module of the acquisition duration and weight, is used for on the basis of the total acquisition duration of single day and rank score of every goal of all goals, set time to the acquisition duration of every goal, and divide the total acquisition duration of said single day and assign the weight to every time quantum, the said weight is confirmed according to the violation situation of each goal;
the acquisition sequence acquisition module is used for carrying out reverse alignment on the maximum value of the rating score and the minimum value of the weight to obtain the acquisition sequence of each target;
the video stream acquisition module is used for controlling the on-site monitoring device of each target in sequence according to the acquired acquisition sequence and the acquisition time duration to acquire video streams according to the acquisition time duration;
and the violation identification module is used for carrying out violation identification on the image frames in the acquired video stream based on a preset identification model.
An embodiment of the present invention further provides an electronic device, including:
a memory storing execution instructions; and
a processor executing execution instructions stored by the memory to cause the processor to perform the method as described above.
The embodiment of the present invention further provides a readable storage medium, in which an execution instruction is stored, and the execution instruction is used for implementing the method described above when executed by a processor.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes may be made to the present invention by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An intelligent monitoring method for different catering kitchens is characterized by comprising the following steps:
collecting target related data information, generating an index set through quantization processing, and calculating a rating score of a target based on the index set, wherein the data information comprises target basic information, qualification permission information, negative information and administrative penalty information;
on the basis of the total single-day acquisition time of all the targets and the rating scores of all the targets, performing acquisition time timing on all the targets, dividing the total single-day acquisition time and giving a weight to each time period, wherein the weight is determined according to the violation condition of each target;
carrying out reverse alignment on the maximum value of the rating score and the minimum value of the weight to obtain the acquisition sequence of each target;
sequentially controlling the on-site monitoring devices of all targets to acquire video streams according to the acquired acquisition sequence and the acquisition time timing;
and carrying out violation identification on the image frames in the acquired video stream based on a preset identification model.
2. The intelligent monitoring method for different catering kitchens as claimed in claim 1, wherein the collecting target related data information, and generating an index set through a quantization process comprises:
collecting target scale size, grade, duration, number of employees, complaint information, permission information, and administrative penalty information;
and generating an index set by a frequency statistics or segmentation assignment mode.
3. The intelligent monitoring method for different catering kitchens as claimed in claim 2, wherein before calculating the target's rank score based on the set of indicators further comprises:
the index set is normalized according to the following formula:
in the above formula, XnIndicates the nth index, mu, in the index setnMeans, σ, representing the n-th index of the setnIndicating the standard deviation of the nth index in the set of indices.
4. An intelligent monitoring method for different catering kitchens as claimed in claim 3, wherein the expression of the target rating score calculated based on the index set is as follows:
in the above formula, SmRepresents the m-th target rating score, the higher the score, the better the grade, betanAnd b represents the weight of the nth index in the index set, and b represents an intercept item.
5. The intelligent monitoring method for different catering kitchens as claimed in claim 4, wherein the expression of the time-matching of the collection of each target based on the total collection time of each day of all targets and the ranking score of each target is as follows:
in the above formula, tmRepresents the m-th objectWhen the acquisition time duration of (a) is timed, t represents the total acquisition time duration of all targets per day, OmRepresents the floating acquisition time, S, of the mth targetiIndicating the rank score of the ith target.
6. An intelligent monitoring method for different catering kitchens as claimed in claim 5, wherein the preset identification model is obtained by the following way:
randomly acquiring image frames from video streams of all targets, and constructing a sample set by carrying out violation type labeling treatment on the image frames;
taking a sample set as input, training by adopting a deep learning algorithm YOLOv3, and generating a recognition model, wherein the output result of the recognition model comprises violation probability and violation type, and the violation probability is determined by a violation probability threshold.
7. The intelligent monitoring method for different catering kitchens as claimed in claim 6, wherein after the violation identification of the image frames in the captured video stream based on the preset identification model, further comprising:
updating the weight of each time period in the acquisition sequence based on the violation identification result output by the identification model, wherein the formula is as follows:
in the above formula, ωmWeight, g, representing the m-th time periodmRepresenting the number of violations in the m-th time slot in the violation identification result, giRepresenting the number of violations of the ith time slot in the violation identification result;
and updating the rating scores of all the targets based on the violation identification result output by the identification model, wherein the formula is as follows:
in the above formula, a and b are harmonic coefficients, z is the number of frames in the video stream corresponding to the mth target, k is the number of violations in the video stream corresponding to the mth target,
the violation type at the jth violation coordinate of the ith image frame in the video stream is lijCoefficient of time expansion, PijThe probability of violation at the jth violation coordinate of the ith image frame is obtained;
the collection order is updated based on the updated weights and the rank scores.
8. An intelligent monitoring system for different catering kitchens, applied to the method as claimed in any one of claims 1 to 7, comprising:
the system comprises a rating score calculation module, a rating score calculation module and a rating score calculation module, wherein the rating score calculation module is used for collecting target related data information, generating an index set through quantitative processing, and calculating a rating score of a target based on the index set, and the data information comprises target basic information, qualification permission information, negative information and administrative penalty information;
the acquisition module of the acquisition duration and weight, is used for on the basis of the total acquisition duration of single day and rank score of every goal of all goals, set time to the acquisition duration of every goal, and divide the total acquisition duration of said single day and assign the weight to every time quantum, the said weight is confirmed according to the violation situation of each goal;
the acquisition sequence acquisition module is used for carrying out reverse alignment on the maximum value of the rating score and the minimum value of the weight to obtain the acquisition sequence of each target;
the video stream acquisition module is used for sequentially controlling the on-site monitoring devices of all targets to acquire video streams according to the acquired acquisition sequence and the acquisition time timing;
and the violation identification module is used for carrying out violation identification on the image frames in the acquired video stream based on a preset identification model.
9. An electronic device, comprising:
a memory storing execution instructions; and
a processor executing execution instructions stored by the memory to cause the processor to perform the method of any of claims 1 to 7.
10. A readable storage medium having stored therein execution instructions, which when executed by a processor, are configured to implement the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111488628.7A CN114298489B (en) | 2021-12-07 | 2021-12-07 | Intelligent monitoring method, system and storage medium for different catering post-kitchen |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111488628.7A CN114298489B (en) | 2021-12-07 | 2021-12-07 | Intelligent monitoring method, system and storage medium for different catering post-kitchen |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114298489A true CN114298489A (en) | 2022-04-08 |
| CN114298489B CN114298489B (en) | 2024-09-13 |
Family
ID=80964923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111488628.7A Active CN114298489B (en) | 2021-12-07 | 2021-12-07 | Intelligent monitoring method, system and storage medium for different catering post-kitchen |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114298489B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115035712A (en) * | 2022-04-27 | 2022-09-09 | 银江技术股份有限公司 | Method, system, device and medium for recommending urban traffic signal control scheme |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008027211A (en) * | 2006-07-21 | 2008-02-07 | Toto Ltd | Kitchen evaluation method |
| US20130132696A1 (en) * | 2011-11-21 | 2013-05-23 | Hitachi, Ltd. | Storage system management apparatus and management method |
| CN110062199A (en) * | 2018-01-19 | 2019-07-26 | 杭州海康威视系统技术有限公司 | Load-balancing method, device and computer readable storage medium |
| CN110113567A (en) * | 2019-04-01 | 2019-08-09 | 北京金和网络股份有限公司 | Equipment operation monitoring method based on big data technology |
| CN110348733A (en) * | 2019-07-09 | 2019-10-18 | 上海秒针网络科技有限公司 | The determination method and device of checks sequence |
| CN113485422A (en) * | 2021-07-07 | 2021-10-08 | 南京航空航天大学 | Chargeable unmanned aerial vehicle distribution method capable of maximizing monitoring time |
-
2021
- 2021-12-07 CN CN202111488628.7A patent/CN114298489B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008027211A (en) * | 2006-07-21 | 2008-02-07 | Toto Ltd | Kitchen evaluation method |
| US20130132696A1 (en) * | 2011-11-21 | 2013-05-23 | Hitachi, Ltd. | Storage system management apparatus and management method |
| CN110062199A (en) * | 2018-01-19 | 2019-07-26 | 杭州海康威视系统技术有限公司 | Load-balancing method, device and computer readable storage medium |
| CN110113567A (en) * | 2019-04-01 | 2019-08-09 | 北京金和网络股份有限公司 | Equipment operation monitoring method based on big data technology |
| CN110348733A (en) * | 2019-07-09 | 2019-10-18 | 上海秒针网络科技有限公司 | The determination method and device of checks sequence |
| CN113485422A (en) * | 2021-07-07 | 2021-10-08 | 南京航空航天大学 | Chargeable unmanned aerial vehicle distribution method capable of maximizing monitoring time |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115035712A (en) * | 2022-04-27 | 2022-09-09 | 银江技术股份有限公司 | Method, system, device and medium for recommending urban traffic signal control scheme |
| CN115035712B (en) * | 2022-04-27 | 2023-11-14 | 银江技术股份有限公司 | Urban traffic signal control scheme recommendation method, system, device and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114298489B (en) | 2024-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112446025A (en) | Federal learning defense method and device, electronic equipment and storage medium | |
| CN110210624A (en) | Execute method, apparatus, equipment and the storage medium of machine-learning process | |
| JP2022141931A (en) | Method and device for training living body detection model, method and apparatus for living body detection, electronic apparatus, storage medium, and computer program | |
| CN115828112B (en) | Fault event response method and device, electronic equipment and storage medium | |
| CN113128478B (en) | Model training method, pedestrian analysis method, device, equipment and storage medium | |
| CN111860377A (en) | Live broadcast method and device based on artificial intelligence, electronic equipment and storage medium | |
| CN114997263A (en) | Training rate analysis method, device, equipment and storage medium based on machine learning | |
| CN114298489A (en) | Intelligent monitoring method and system for different catering kitchens and storage medium | |
| CN115239508A (en) | Scene planning adjustment method, device, equipment and medium based on artificial intelligence | |
| CN113706291A (en) | Fraud risk prediction method, device, equipment and storage medium | |
| CN111126155B (en) | Pedestrian re-identification method for generating countermeasure network based on semantic constraint | |
| CN112069039A (en) | Monitoring and predicting alarm method and device for artificial intelligence development platform and storage medium | |
| CN115222443A (en) | Client group division method, device, equipment and storage medium | |
| CN107784482A (en) | Recruitment methods, electronic installation and readable storage medium storing program for executing | |
| CN111950507B (en) | Data processing and model training method, device, equipment and medium | |
| CN111814653B (en) | Method, device, equipment and storage medium for detecting abnormal behavior in video | |
| CN115131826B (en) | Article detection and identification method, and network model training method and device | |
| CN117132000A (en) | Crop growth condition prediction method, device and medium based on AI | |
| CN116434973A (en) | Infectious disease early warning method, device, equipment and medium based on artificial intelligence | |
| CN106454233A (en) | Intelligent crowd-gathering monitoring method and system | |
| CN114882420A (en) | Reception people counting method and device, electronic equipment and readable storage medium | |
| CN115169360A (en) | User intention identification method based on artificial intelligence and related equipment | |
| CN112989869B (en) | Optimization method, device, equipment and storage medium of face quality detection model | |
| CN113963413A (en) | Epidemic situation investigation method and device based on artificial intelligence, electronic equipment and medium | |
| CN113312482A (en) | Question classification method and device, electronic equipment and readable storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |