CN117573924A

CN117573924A - Kitchen data processing method and electronic equipment

Info

Publication number: CN117573924A
Application number: CN202410067170.5A
Authority: CN
Inventors: 陈建波; 晏阳; 田西艳
Original assignee: Lazas Network Technology Shanghai Co Ltd; Koubei Shanghai Information Technology Co Ltd
Current assignee: Lazas Network Technology Shanghai Co Ltd; Koubei Shanghai Information Technology Co Ltd
Priority date: 2024-01-16
Filing date: 2024-01-16
Publication date: 2024-02-20

Abstract

The application discloses a kitchen data processing method and electronic equipment. The method comprises the following steps: initiating a first task for determining a video acquisition parameter set; the first task comprises determining a configuration parameter set matched with a merchant and a risk layering parameter set matched with a risk level of the merchant to which the merchant belongs, and determining a video acquisition parameter set corresponding to the merchant according to the configuration parameter set and the risk layering parameter set; wherein the video acquisition parameter set at least indicates the acquisition period of kitchen video data of a merchant matching the corresponding parameter set; and starting a second task for acquiring kitchen video data, wherein the second task comprises the steps of determining a current acquisition merchant for acquiring the kitchen video data according to the video acquisition parameter set, and acquiring the kitchen video data of the current acquisition merchant from a kitchen video source. By adopting the method, the problem of low effectiveness of kitchen collected data is solved.

Description

Kitchen data processing method and electronic equipment

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to a kitchen data processing method, device, electronic apparatus, and storage medium.

Background

With the development of the catering industry, especially the popularization of online meal ordering, the food safety problem is more and more important. In order to strengthen the management of the catering industry, video monitoring of the kitchen is a key means.

In the prior art, video monitoring is carried out on a kitchen in the catering industry to identify the problems of mess, irregular operation and the like. However, when merchants needing to monitor reach a certain scale, massive videos need to be recognized and analyzed in time for finding food safety problems in real time, so that the consumption of hardware resources for calculation is challenging.

Therefore, how to control the acquisition of kitchen video data to reduce invalid sampling data and ensure the validity of the acquired data is a problem to be solved.

The above information disclosed in the background section is only for enhancement of understanding of the background of the application and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art.

Disclosure of Invention

The kitchen data processing method solves the problem that the effectiveness of kitchen collected data is low.

The embodiment of the application provides a kitchen data processing method, which comprises the following steps: starting a first task for determining a video acquisition parameter set, wherein the first task is used for determining the video acquisition parameter set corresponding to a merchant of kitchen video data to be acquired; the first task comprises determining a configuration parameter set matched with a merchant and a risk layering parameter set matched with a risk level of the merchant to which the merchant belongs, and determining a video acquisition parameter set corresponding to the merchant according to the configuration parameter set and the risk layering parameter set; wherein the video acquisition parameter set at least indicates the acquisition period of kitchen video data of a merchant matching the corresponding parameter set; and starting a second task for acquiring kitchen video data, wherein the second task comprises the steps of determining a current acquisition merchant for acquiring the kitchen video data according to the video acquisition parameter set, and acquiring the kitchen video data of the current acquisition merchant from a kitchen video source.

Optionally, the method further comprises: the first task includes obtaining a rush hour parameter set configured for a rush hour period; the determining the video acquisition parameter set corresponding to the merchant according to the configuration parameter set and the risk stratification parameter set comprises the following steps: determining a parameter set with the shortest acquisition period as a video acquisition parameter set of the merchant according to the peak period parameter set, the configuration parameter set and the risk layering parameter set; or taking the parameter set with the highest priority among the peak period parameter set, the configuration parameter set and the risk layering parameter set as the video acquisition parameter set of the merchant.

Optionally, the method further comprises: the first task includes obtaining a global parameter set, and using the global parameter set as a video acquisition parameter set of a merchant not matching any parameter set of the upper configuration parameter set, the risk stratification parameter set and the peak period parameter set: and/or, the first task comprises determining that the acquisition time for kitchen video data acquisition matches with a rush hour period and successfully acquiring a rush hour parameter set, and taking the rush hour parameter set as the video acquisition parameter set of the merchant at the acquisition time.

Optionally, the method further comprises: the first task comprises carrying out peak period parameter set matching aiming at a merchant, and if the acquisition time of the merchant for kitchen video data acquisition is determined to be not matched with the peak period or the peak period parameter set is not successfully acquired, determining whether the merchant is matched with a valid configuration parameter set and/or risk layering parameter set; if the merchant is not matched with any effective configuration parameter set and/or risk layering parameter set, taking the global parameter set as a video acquisition parameter set of the merchant; the method further comprises the steps of: the first task comprises, for a risk-free merchant with a risk level of the merchant, taking the peak period parameter set as a video acquisition parameter set of the risk-free merchant if the peak period parameter set is determined to be matched with the peak period currently and the peak period parameter set is acquired; if the current unmatched peak period or the unsuccessfully acquired peak period parameter set is determined, acquiring a matched configuration parameter set of each risk-free merchant as a video acquisition parameter set of the corresponding merchant; and if the configuration parameter set is not successfully acquired, taking the global parameter set as a video acquisition parameter set of the risk-free merchant.

Optionally, the configuration parameter set includes: a regional parameter set configured for the designated region and/or a merchant list parameter set configured for the designated merchant; the determining the matched configuration parameter set of the merchant includes: determining whether the merchant hits the regional parameter set according to regional information corresponding to the merchant, and if so, taking the regional parameter set as a configuration parameter set matched with the merchant; and/or determining whether the merchant hits the merchant list parameter set according to the merchant name of the merchant, if so, taking the merchant list parameter set as the matched configuration parameter set of the merchant; and if the matched configuration parameter set of the merchant comprises a regional parameter set and a merchant list parameter set, taking the parameter set with a shorter sampling period as the video acquisition parameter set of the merchant, or taking the parameter set with a higher priority as the video acquisition parameter set of the merchant.

Optionally, the determining the configuration parameter set matched with the merchant and the risk layering parameter set matched with the risk level of the merchant to which the merchant belongs, and determining the video acquisition parameter set corresponding to the merchant according to the configuration parameter set and the risk layering parameter set, includes: determining the risk level of each merchant according to the historical abnormal data, and acquiring a risk layering parameter set matched with the risk level of each merchant; taking the parameter set with the shortest acquisition period in the configuration parameter set and the risk wind acquisition parameter set as the video acquisition parameter set; storing the video acquisition parameter set of the commercial tenant to a message area corresponding to the acquisition period; the determining, according to the video collection parameter set, a current collection merchant that performs kitchen video data collection currently, and collecting kitchen video data of the current collection merchant from a kitchen video source, includes: acquiring a current acquisition merchant from a message area corresponding to the acquisition period according to the acquisition period; and acquiring the kitchen video data of the current acquisition merchant from the kitchen video source path according to the video acquisition parameter set indication of the current acquisition merchant.

Optionally, the method further comprises: the first task is a timing task; the first task comprises the step of generating a video acquisition table in a first task period according to a video acquisition parameter set of a merchant and an execution period of the first task; the video acquisition table comprises acquisition time of each merchant in a first task period; the second task includes determining a current acquisition merchant currently performing kitchen video data acquisition according to the video acquisition parameter set, including: and the second task queries the merchant with the acquisition time matched with the current time from the video acquisition table as the current acquisition merchant.

Optionally, the method further comprises: starting a third task, wherein the third task and the second task are executed asynchronously to realize that kitchen video data of the current acquisition merchant are acquired from a kitchen video source; the second task includes determining a current acquisition merchant currently performing kitchen video data acquisition according to the video acquisition parameter set, acquiring kitchen video data of the current acquisition merchant from a kitchen video source, including: the second task adds the information of the current acquisition merchant to an acquisition queue or to a time chain according to the acquisition time of each merchant in the video acquisition table; and the third task comprises reading the message node from the collection queue or the time chain, and collecting kitchen video data of the current collection merchant from a kitchen video source according to the current collection merchant corresponding to the message node.

Optionally, the method further comprises: starting a fourth task for adjusting the risk level of the merchant to which the merchant belongs; the fourth task is a timing task and is executed asynchronously with the first task; the fourth task comprises the steps of obtaining historical abnormal data of a merchant and determining a merchant risk level to which the merchant belongs according to the historical abnormal data; wherein the determining, according to the historical abnormal data, the merchant risk level to which the merchant belongs includes: if no abnormal data exists in a first specified number of continuous time periods, dividing the merchant into risk-free merchants; if there is abnormal data for each time period within a first specified number of consecutive time periods, classifying the merchant into a first risk level; dividing the merchant into a second risk level if there is anomalous data within a first specified number of consecutive time periods and the anomalous data is within a second specified number of consecutive time periods; if there is abnormal data in the first specified number of consecutive time periods and the abnormal data is in the third specified time period, dividing the merchant into a third risk level; the first specified number of consecutive time periods includes the second specified number of consecutive time periods and the third specified time period; wherein the method further comprises: receiving a set of merchant risk levels for specified merchants, the specified merchants identified as specified risk merchants with specified risk levels; the fourth task includes eliminating the specified risk merchant when the merchant risk level to which the merchant belongs is adjusted so as to maintain the merchant risk level configured for the specified risk merchant.

Optionally, the acquiring the kitchen video data of the current acquisition merchant from the kitchen video source includes: acquiring sampling time length according to the video acquisition parameter set; determining an initial kitchen video of the current time corresponding to the current acquisition merchant from the kitchen video source; identifying a key frame containing foreground information from the initial kitchen video, and intercepting kitchen video data from the key frame to the time length indicated by the sampling duration as the kitchen video data collected at this time; or, performing frame extraction from the initial kitchen video according to a preset frame extraction parameter set to obtain kitchen video data with sampling duration indicating time length, wherein the preset frame extraction parameter set at least comprises frame extraction frequency set based on sampling time and/or sampling area.

Optionally, the method further comprises: initiating a fifth task for identifying kitchen video data; the fifth task includes, for the collected kitchen video data, identifying a video frame including an abnormal picture and saving the video frame as a food safety risk video; if the food security risk video corresponds to the night peak period, pest identification is carried out on video data of a risk merchant corresponding to the food security risk video in the night peak period, first early warning information for indicating environmental sanitation problems is generated and sent to the risk merchant; if the food security risk video corresponds to a food production peak period, identifying operation abnormality and/or producer dressing abnormality in a production flow, generating second early warning information for indicating the production flow abnormality, and sending the second early warning information to the risk merchant; if the food security risk video corresponds to the food taking area, identifying abnormal food taking flow, storing the abnormal food taking flow and an order of a corresponding period in a correlated manner, generating third early warning information for indicating the abnormal food taking flow, and sending the third early warning information to the risk merchant.

Optionally, the method further comprises: receiving configuration information aiming at a configuration parameter set and/or a risk layering parameter set, wherein the configuration information comprises sampling periods and/or parameter set priorities indicated by the corresponding parameter sets; checking whether the time length sequence of the sampling periods of different parameter sets accords with a preset standard sequence or not according to the configuration information, and if not, generating prompt information that the sampling periods are inconsistent with the preset standard sequence; and/or checking whether the parameter set priorities of different parameter sets accord with a preset priority order aiming at the configuration information, if not, generating prompt information of which the priorities are inconsistent with the preset priority order; and validating the configuration information in response to confirming the continued configuration for the prompt information.

The embodiment of the application also provides electronic equipment, which comprises: a memory, and a processor; the memory is used for storing a computer program, and the computer program is executed by the processor to execute the method provided by the embodiment of the application.

The embodiment of the application also provides a computer storage medium, which stores computer-executable instructions for implementing the method provided in the embodiment of the application when the computer-executable instructions are executed by a processor.

Compared with the prior art, the application has the following advantages:

according to the kitchen data processing method, the kitchen data processing device, the electronic equipment and the storage medium, a first task for determining a video acquisition parameter set is started, and the first task is used for determining the video acquisition parameter set corresponding to a merchant for acquiring kitchen video data; the first task comprises determining a configuration parameter set matched with a merchant and a risk layering parameter set matched with a risk level of the merchant to which the merchant belongs, and determining a video acquisition parameter set corresponding to the merchant according to the configuration parameter set and the risk layering parameter set; wherein the configuration parameter set and the risk stratification parameter set at least indicate a collection period of kitchen video data of a merchant hitting the corresponding parameter set; and starting a second task for acquiring kitchen video data, wherein the second task comprises the steps of determining a current acquisition merchant for acquiring the kitchen video data according to the video acquisition parameter set, and acquiring the kitchen video data of the current acquisition merchant from a kitchen video source. Therefore, the collection period can be designated through the configuration parameter set of the merchant and/or the risk layering parameter set corresponding to the merchant risk level, and the problem of low effectiveness of kitchen collection data is at least partially solved. And the calculation of the video acquisition parameter set and the kitchen data acquisition are decoupled into different task execution, so that the processing efficiency can be improved. Further, the fourth task is used for adjusting the risk level of the commercial tenant, different risk layering parameter sets can be configured according to video acquisition requirements by different risk levels of the commercial tenant, and corresponding acquisition periods or acquisition frequencies are arranged in the risk layering parameter sets, so that automatic frequency raising or frequency lowering of the acquisition frequencies is realized, the effectiveness of kitchen data acquisition is improved, and the consumption of hardware resources is reduced.

Drawings

Fig. 1 is a process flow diagram of a kitchen data processing method according to a first embodiment of the present application.

Fig. 2 is a risk stratification flow for adjusting a risk level of a merchant according to a first embodiment of the present application.

Fig. 3 is a calculation flow of a video acquisition parameter set according to the first embodiment of the present application.

Fig. 4 is a schematic view of a kitchen data processing device according to a second embodiment of the present application.

Fig. 5 is a schematic diagram of an electronic device provided in the present application.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is, however, susceptible of embodiment in many other ways than those herein described and similar generalizations can be made by those skilled in the art without departing from the spirit of the application and the application is therefore not limited to the specific embodiments disclosed below.

The embodiment of the application provides a kitchen data processing method, a kitchen data processing device, electronic equipment and a storage medium. The following examples are described in detail.

The kitchen data processing method provided by the embodiment of the application can be applied to a system environment comprising a configuration management client and a server. A parameter set-related configuration for controlling kitchen video acquisition is received by a configuration management client. The parameter set indicates at least a capture period or capture frequency of kitchen video data of a merchant hitting the parameter set. In practice, the parameter set of a specific acquisition scheme can be designed according to the kitchen video acquisition requirements in different scenes. An exemplary parameter set design includes: global parameter set, configuration parameter set, merchant risk layering parameter set, peak period parameter set; the merchant can hit one or more parameter sets, and the parameter set for collecting kitchen video data is selected from the hit parameter sets according to a preset rule to be the video collection parameter set. The global parameter set is a global mode for controlling the acquisition period and/or controlling the frame extraction logic when acquiring the video, that is, the kitchen video can be acquired by a full-scale catering merchant accessing the system environment under the default of a platform deploying the system environment. By a configuration parameter set, it is understood a local parameter set for controlling the acquisition period and/or controlling the frame extraction logic when acquiring video for merchants hitting the corresponding configuration parameter set. The configuration parameter set may include a regional parameter set, a merchant list parameter set, and the like. For example, a regional parameter set is configured for a region, i.e. whether the merchant hits the configured regional parameter set is determined according to the geographic region to which the merchant belongs, and then a merchant list parameter set is configured, i.e. whether the merchant hits the configured merchant list parameter set is determined according to the merchant identifier or the merchant name. Each configured set of configuration parameters may individually configure the acquisition period or acquisition frequency. In a parameter set design mode, the priority of the configuration parameter set is higher than that of the global parameter set, and if the configuration parameter set is hit by a merchant, the configuration parameter set is used as a video acquisition parameter set for acquiring kitchen videos. The peak period parameter set is a parameter set according to the characteristics of the catering industry and aiming at a specified time period, for example, the parameter set is arranged at the peak period of food production such as lunch, dinner and the like, so that the sampling frequency can be increased, and videos of each order production are collected to provide a data basis for backtracking of food safety events; for another example, a parameter set is set for a period of night time in which the mice are not on peak, such as early morning. In one parameter set design manner, the priority of the peak period parameter set is higher than the priority of the configuration parameter set and the priority of the risk layering parameter set, that is, even if the user hits other configuration parameter sets and risk layering parameter sets in the peak period, the peak period parameter set is taken as the video acquisition parameter set, and if the user does not hit the other configuration parameter sets and risk layering parameter sets in the peak period, the parameter set with the higher priority or the parameter set with a shorter sampling period is taken as the video acquisition parameter set. The merchant risk layering parameter set is a parameter set corresponding to the layering for carrying out risk grading on merchants according to the risk grading of the merchants, and carrying out risk layering on the merchants according to the merchant risk layering of different risk grades. An exemplary merchant risk stratification includes: dividing merchants with food safety risks identified in three consecutive months into first risk classes, such as red risk merchants, setting the sampling period of a first risk class parameter set to be shorter, and collecting kitchen videos every 5 minutes; dividing merchants with food safety risks in two consecutive months into second risk classes such as orange risk merchants, and setting the sampling period of the second risk class parameter set to 15 minutes; merchants with food safety risk for nearly one month are classified as third risk classes, such as yellow risk merchants, and the sampling period of the third risk class parameter set is set to 30 minutes. For a risk-free merchant, other parameter sets, such as a configuration parameter set, a global parameter set, etc., are hit. Therefore, layering of merchants is achieved, different video acquisition periods are adopted, and effectiveness of video acquisition is improved. The timing task can automatically adjust the affiliated merchant risk level aiming at the merchant, and the merchant risk layering parameter set is combined, so that the acquisition frequency of the kitchen video is automatically improved or reduced, and the video acquisition efficiency is improved. Of course, the configuration management client also receives a specified risk stratification-related configuration for specifying a merchant risk level to which one or more merchants belong. For the merchant with the specified merchant risk level, the timing task for automatically adjusting the merchant risk level is not processed.

The server receives configuration information sent by the configuration management client, determines a video acquisition parameter set of kitchen video data of the businesses according to the configuration information in effect, acquires the kitchen video data of the businesses in a targeted manner according to an acquisition period or an acquisition frequency indicated by the video acquisition parameter set hit by each business, so as to obtain an effective video, identifies a security risk video containing an abnormal picture according to the acquired kitchen video data, associates the security risk video with the business information and stores the security risk video, is convenient for sending early warning prompt information to the businesses according to the security risk video, promotes the businesses to treat, and solves the kitchen food security problem.

The configuration management client can be a computer used for operation management and the like of a catering industry platform. The server may be a back-end server for processing kitchen video data of the merchant, etc.

Of course, a merchant client may also be included in the system environment. After the server side identifies the abnormal video, the related data and/or early warning prompt information of the abnormal video can be sent to the merchant client side to inform the merchant, so that the server side is convenient to take treatment measures in time, and the food safety problem is solved.

It should be noted that the above disclosed information is only used to aid in understanding the present application, and is not meant to constitute prior art known to those of ordinary skill in the art.

A kitchen data processing method provided in a first embodiment of the present application will be described with reference to fig. 1 to 3. The kitchen data processing method shown in fig. 1 comprises the following steps: step S101 to step S102.

Step S101, a first task for determining a video acquisition parameter set is started, wherein the first task is used for determining the video acquisition parameter set corresponding to a merchant for which kitchen video data are to be acquired.

Specifically, the kitchen environment is complex in constitution, the kitchen related space is divided into a plurality of key areas, the camera equipment is arranged, initial data are obtained by the camera equipment to serve as a kitchen video source, kitchen video data of each merchant are sampled from the kitchen video source, and food safety risks are further identified. In this embodiment, the video acquisition parameter set of the merchant controls the acquisition frequency of the kitchen video data of the merchant, so as to reduce the consumption of hardware resources as much as possible and reduce invalid video sampling data, and further detect the video data, such as pests, staff, manufacturing processes, early meal preparation areas, manufacturing areas, manufactured food packaging areas, and the like, which are acquired in the kitchen of the merchant and are related to food safety, comprehensively judge the food safety condition, and early warn against abnormal situations. Thereby improving the monitoring efficiency of food safety.

Specifically, the kitchen related space can be divided into a raw material acceptance area, a raw material storage area, a preliminary meal preparation area (including raw material cleaning, preparation and the like), a preparation area, a food preparation circulation area, a food packing area, a food preparation appliance and meal appliance cleaning and sterilizing area, a food preparation appliance and meal appliance storage area, a kitchen door area, a meal preparation room door area and other key areas; and recording the kitchen video source in the dimension of the commercial tenant or recording the kitchen video source in the dimension of key areas of different commercial tenants for acquiring the kitchen video data.

In this embodiment, in order to improve the effectiveness of the collected kitchen video data, different collection schemes may be formulated, and the collection of the kitchen video data of each merchant may be controlled by the parameter set corresponding to the collection scheme. The parameter set is indicative of at least a collection period. In one embodiment, a global parameter set that can be hit by each merchant is included, as well as a configuration parameter set and/or merchant risk stratification parameter set for controlling the acquisition frequency of a portion of the merchants. The global parameter set is a default hit parameter set of each merchant. The configuration parameter set is a parameter set hit by part of merchants, and can be further subdivided into a regional parameter set, a merchant list parameter set and the like. The merchant risk layering parameter set is a merchant risk grade layering of food security risks for merchants by a pointer, and different parameter sets are preset for merchants with different risk layering. Different collection parameter sets can be set for different merchant risk levels. In one embodiment, the system further comprises a peak period parameter set configured for peak periods, and the peak period parameter set is used for controlling the acquisition frequency and/or frame extraction logic of each merchant in the peak period. The parameter set may also indicate frame extraction logic for controlling a frame extraction processing mode when kitchen video data is collected for a merchant hitting the parameter set. The parameter set may also indicate a sampling duration. Of course, other parameter set designs may be used, all of which are within the scope of the present application. In one embodiment, the period of effectiveness of the parameter set may be specified when the parameter set is set. Therefore, kitchen video data are collected by merchants hitting the parameter set in different time periods through the collection period and/or frame extraction logic indicated by the parameter set. The above embodiments may be combined with each other without collision.

Specifically, examples of parameter set-related configurations are as follows: (1) For the global parameter set, camera data are collected every 2 hours, and all merchants hit the global parameter set by default. (2) The regional parameter set can be formulated according to the urban region, and can also be formulated according to different geographic regions of the city. (3) Parameter sets can be formulated according to business categories and/or business periods to which the merchant belongs, for example, corresponding configuration parameter sets are formulated for different business categories and business periods such as afternoon tea, breakfast, overnight and the like, so that corresponding acquisition period and/or frame extraction logic are adopted according to business characteristics of the merchant. In addition, the acquisition period (or acquisition frequency) may be configured separately for each parameter set, such as acquisition once every 4 hours, etc. The configuration mode of the acquisition period can be a mode of selection or input, for example, the configuration acquisition period is 5 minutes, 10 minutes, 15 minutes, 20 minutes, 30 minutes, 40 minutes, 45 minutes, 60 minutes, 90 minutes, 2 hours, 3 hours, 4 hours, 6 hours, 8 hours, and the like.

In this embodiment, the peak period parameter set may be determined according to a business class and/or a business period to which the merchant belongs. Also, the rush hour parameter set may be set for different critical areas. For example, regarding lunch periods (10:00-12:00 am), dinner periods (17:00-19:00) as production rush hour periods, a rush hour parameter set is set for the following key areas: the front meal preparation area (including raw material cleaning, preparation and the like), the manufacturing area, the food production circulation area, the food production packaging area, the food production tool and meal tool cleaning and disinfecting area, the food production tool and meal tool preservation area and the like are used for facilitating control of video monitoring and identification of the artificial health risks related to the manual production of food at a higher acquisition frequency. For another example, using the early morning hours (2:00-4:00 pm) as the rush hour time sets parameters for the following critical areas: raw material storage area, preliminary meal preparation area (including raw material cleaning, preparation, etc.), manufacturing area, thereby facilitating control of video monitoring and identification of environmental health risks related to pest emergence at higher acquisition frequencies.

In this embodiment, the relevant processing procedure for acquiring the kitchen video data is decoupled into a parameter set configuration task, a parameter set calculation task for determining a video acquisition parameter set, and a video acquisition task for acquiring the kitchen video data, so as to improve the processing flexibility and the processing efficiency. The parameter set configuration task is a task for executing a parameter set configuration command. Specifically, the parameter set configuration task is a front-end task, and is configured to receive configuration information of a parameter set input by an operation user using a configuration management client, store the configuration information after performing input validity check, and enable the configuration information to be effective, so that the first task obtains configuration information related to the parameter set to calculate an actual video acquisition parameter set of a merchant according to the configuration information. The parameter set configuration task specifically comprises the following steps: receiving configuration information aiming at a configuration parameter set and/or a risk layering parameter set, wherein the configuration information comprises sampling periods and/or parameter set priorities indicated by the corresponding parameter sets; checking whether the time length sequence of the sampling periods of different parameter sets accords with a preset standard sequence or not according to the configuration information, and if not, generating prompt information that the sampling periods are inconsistent with the preset standard sequence; and/or checking whether the parameter set priorities of different parameter sets accord with a preset priority order aiming at the configuration information, if not, generating prompt information of which the priorities are inconsistent with the preset priority order; and validating the configuration information in response to confirming the continued configuration for the prompt information. Of course, a merchant list provided by a third party and required to be monitored can be imported, and a merchant list parameter set is generated according to monitoring requirement information of merchants in the merchant list.

Specifically, the first task is a parameter set calculation task, the second task is a video acquisition task, and the first task and the second task are back-end tasks. In one embodiment, the method is processed in a T+1 mode, the first task calculates the video acquisition parameter set of each merchant according to the data of the previous natural day in the early morning, so that the total table comprising the video acquisition parameter set of each merchant can be calculated, and merchants with different acquisition periods can be classified and written into the message areas corresponding to the acquisition periods according to the acquisition periods. The second task may be executed in a unit time as a period (for example, executed by a timer every minute), and when an acquisition period is reached, the corresponding merchant is queried in the summary table or the message area corresponding to the acquisition period is polled to read the corresponding merchant, so as to obtain kitchen video data of the corresponding merchant. In other embodiments, the video acquisition task may also be decoupled into a second task and a third task. The second task is used for acquiring the commercial tenant to be acquired at the current time according to the video acquisition parameter set of each commercial tenant calculated by the first task, constructing a current acquisition message chain or writing the acquisition information of each commercial tenant into a message area corresponding to each acquisition period in a classified manner; and a third task, configured to read a message from the message chain or poll the corresponding message area according to different acquisition periods, access the kitchen video source for merchant information corresponding to the message, and extract a video frame from the kitchen video source according to frame extraction logic indicated by a video acquisition parameter set of the merchant, so as to obtain kitchen video data of sampling duration indicated by the video acquisition parameter set, and use the kitchen video data as a data analysis object for identifying food security risks. The different embodiments may be combined with each other without conflict.

In this embodiment, the method further includes layering the risk levels of the merchants, and setting corresponding risk layering parameter sets for the merchants of each risk layering. For example, if a merchant identifies food safety anomalies three months in succession, adding the merchant to a first risk level hierarchy, the hierarchical risk level hierarchy parameter set indicating a collection period of 5 minutes; if food safety abnormality is identified in two continuous months, adding the merchant into a second risk level hierarchy, wherein a risk hierarchy parameter set of the hierarchy indicates a collection period of 15 minutes; if a food safety anomaly was identified in the last month, the merchant is added to a second risk level hierarchy, the risk level hierarchy parameter set of which indicates a collection period of 30 minutes. Furthermore, the first task can be used for risk stratification of the merchant, and the timing task can be started to asynchronously perform risk stratification of the merchant, so that the merchant can automatically move among all risk layers based on historical risk data, and the method specifically comprises the following steps: starting a fourth task for adjusting the risk level of the merchant to which the merchant belongs; the fourth task is a timing task and is executed asynchronously with the first task; the fourth task comprises the steps of obtaining historical abnormal data of a merchant and determining a merchant risk level to which the merchant belongs according to the historical abnormal data; wherein the determining, according to the historical abnormal data, the merchant risk level to which the merchant belongs includes: if no abnormal data exists in a first specified number of continuous time periods, dividing the merchant into risk-free merchants; if there is anomalous data for each period within a first specified number of consecutive periods (e.g., 3 months in succession), then classifying the merchant as a first risk level (e.g., red risk stratification); if there is anomalous data within the first specified number of consecutive time periods and the anomalous data is within a second specified number of consecutive time periods (e.g., approximately 2 months), then classifying the merchant as a second risk level; if there is anomalous data within the first specified number of consecutive time periods and the anomalous data is within a third specified time period (e.g., approximately 1 month), then classifying the merchant as a third risk level; the first specified number of consecutive time periods includes the second specified number of consecutive time periods and the third specified time period; wherein the method further comprises: receiving a set of merchant risk levels for specified merchants, the specified merchants identified as specified risk merchants with specified risk levels; the fourth task includes eliminating the specified risk merchant when the merchant risk level to which the merchant belongs is adjusted so as to maintain the merchant risk level configured for the specified risk merchant. Thus, kitchen video data is conveniently collected for a specified risk merchant with a collection period of a specified merchant risk level.

Referring to fig. 2, a risk stratification process for adjusting a risk level of a merchant is shown, including: the risk level can be specified for the merchant, for example, the merchant is divided into a risk-free layer, a yellow risk layer, an orange risk layer and a red risk layer, wherein the risk-free layer, the yellow risk layer, the orange risk layer and the red risk layer respectively represent different risk levels, different risk degrees are reflected, and the risk-free, yellow, orange and red represent gradual increase of the risk degrees. The figure also includes: and automatically adjusting risk layering corresponding to the merchant according to the historical abnormal data (namely the historical risk data). S201, judging whether the continuous three months are abnormal, and if the continuous three months are abnormal, dividing the merchant into risk-free layering; if not, S202 is performed. S202, judging whether food safety risks occur in the last month, if so, dividing merchants into yellow risk stratification; if not, S203 is performed. S203, judging whether the food safety risk occurs in the next two months, if so, dividing the merchant into orange risk layers; if not, S204 is performed. S204, whether the food safety risk occurs in the last three months, if so, the merchant is classified into red risk stratification. And for merchants with each risk stratification, if judging that no food safety risk occurs in the last three months, continuously judging whether food safety risk occurs in the last two months, if so, adjusting from red risk stratification to orange risk stratification, and so on. Therefore, risk stratification of the merchant is automatically adjusted, corresponding risk stratification parameter sets are configured in combination with each risk stratification, and different collection periods can be indicated by different risk stratification parameter sets, for example, higher collection frequency, namely shorter collection period, can be configured for risk stratification with high risk degree, so that the effect of automatically improving or reducing the video collection frequency of the kitchen of the merchant can be achieved.

Step S102, the first task comprises determining a configuration parameter set matched with a merchant and a risk layering parameter set matched with a risk level of the merchant to which the merchant belongs, and determining a video acquisition parameter set corresponding to the merchant according to the configuration parameter set and the risk layering parameter set; wherein the video acquisition parameter set indicates at least an acquisition period of kitchen video data of a merchant matching the corresponding parameter set.

Specifically, the first task calculates an actual video acquisition parameter set of the merchant. One merchant may hit one or more parameter sets, such as global parameter set, configuration parameter set, risk stratification parameter set, and then select one of the parameter sets from the hit parameter sets as the video capture parameter set. In one embodiment, the first task includes obtaining a rush hour parameter set configured for a rush hour period; the determining the video acquisition parameter set corresponding to the merchant according to the configuration parameter set and the risk stratification parameter set comprises the following steps: determining a parameter set with the shortest acquisition period as a video acquisition parameter set of the merchant according to the peak period parameter set, the configuration parameter set and the risk layering parameter set; or taking the parameter set with the highest priority among the peak period parameter set, the configuration parameter set and the risk layering parameter set as the video acquisition parameter set of the merchant. In one embodiment, the first task includes obtaining a global parameter set as a video capture parameter set for a merchant that does not match any of the upper configuration parameter set, the risk stratification parameter set, and the peak parameter set: and/or, the first task comprises determining that the acquisition time for kitchen video data acquisition matches with a rush hour period and successfully acquiring a rush hour parameter set, and taking the rush hour parameter set as the video acquisition parameter set of the merchant at the acquisition time. In one embodiment, the first task includes performing peak period parameter set matching for a merchant, and if it is determined that the collection time of kitchen video data collection performed by the merchant does not match an upper peak period or the peak period parameter set is not successfully obtained, determining whether the merchant matches an upper effective configuration parameter set and/or risk stratification parameter set; if the merchant is not matched with any effective configuration parameter set and/or risk layering parameter set, taking the global parameter set as a video acquisition parameter set of the merchant; the method further comprises the steps of: the first task comprises, for a risk-free merchant with a risk level of the merchant, taking the peak period parameter set as a video acquisition parameter set of the risk-free merchant if the peak period parameter set is determined to be matched with the peak period currently and the peak period parameter set is acquired; if the current unmatched peak period or the unsuccessfully acquired peak period parameter set is determined, acquiring a matched configuration parameter set of each risk-free merchant as a video acquisition parameter set of the corresponding merchant; and if the configuration parameter set is not successfully acquired, taking the global parameter set as a video acquisition parameter set of the risk-free merchant. The above embodiments may be combined with each other without collision.

In this embodiment, the configuration parameter set includes: a regional parameter set configured for the designated region and/or a merchant list parameter set configured for the designated merchant; correspondingly, the determining the matched configuration parameter set of the merchant includes: determining whether the merchant hits the regional parameter set according to regional information corresponding to the merchant, and if so, taking the regional parameter set as a configuration parameter set matched with the merchant; and/or determining whether the merchant hits the merchant list parameter set according to the merchant name of the merchant, if so, taking the merchant list parameter set as the matched configuration parameter set of the merchant; and if the matched configuration parameter set of the merchant comprises a regional parameter set and a merchant list parameter set, taking the parameter set with a shorter sampling period as the video acquisition parameter set of the merchant, or taking the parameter set with a higher priority as the video acquisition parameter set of the merchant.

Referring to fig. 3, a calculation process of a video acquisition parameter set is shown, which may be performed by a first task, including: s301, acquiring a global parameter set, wherein each merchant defaults to hit the global parameter set, for example, the global parameter set configures the acquisition period to be 2 hours. S302, a configuration parameter set is obtained, wherein the configuration parameter set comprises two types: the method comprises the steps of determining whether a merchant hits the regional parameter set or not according to the regional parameter set and the merchant list parameter set, wherein S303 and S304; s305 and S306 determine whether the merchant hits the merchant list parameter set. Other types of configuration parameter sets may of course be included, for example parameter sets configured by business type (afternoon tea type, dinner type, etc.). S303, acquiring a regional parameter set. S304, judging whether the merchant belongs to the geographical area corresponding to the regional parameter set, and if the geographical area corresponding to the merchant matches the geographical area indicated by the regional parameter set, hitting the regional parameter set. S305, acquiring a merchant list parameter set. S306, judging whether the merchant is in the list range corresponding to the merchant list parameter set, and if the name or the identification of the merchant is in the merchant range indicated by the merchant list parameter set, the merchant hits the merchant list parameter set. S307, acquiring a risk stratification parameter set. S308, judging whether the merchant belongs to a risk hierarchy corresponding to the risk hierarchy parameter set, and if the merchant risk level of the merchant matches the risk hierarchy, hitting the risk level parameter set by the merchant. S309, obtaining a peak period parameter set. And S310, kitchen video data acquisition is executed according to the maximum acquisition frequency, namely, the first task takes a parameter set which is hit by one merchant and contains the maximum acquisition frequency as a video acquisition parameter set of the merchant. The acquisition of kitchen video data may actually be performed by the second task for the merchant according to the set of video parameters. When one merchant hits multiple parameter sets, the shortest acquisition period (i.e., the maximum acquisition frequency) is taken for acquisition. Of course, various types of parameter sets, such as an area parameter set, a merchant list parameter set, a risk stratification parameter set, a peak period parameter set, and the like, may be configured with one or more parameter sets, to indicate different acquisition periods and/or different frame extraction logic, and may even specify different effective time periods, and the like. The present application is not limited.

Step S103, a second task for acquiring kitchen video data is started, wherein the second task comprises determining a current acquisition merchant for acquiring the kitchen video data according to the video acquisition parameter set, and acquiring the kitchen video data of the current acquisition merchant from a kitchen video source.

Specifically, the second task execution collects kitchen video data. In implementation, the first task is a timing task, for example, the first task is executed in the early morning every day, including calculating a video acquisition parameter set of the current day of the merchant; and if the video acquisition parameter set is executed in the morning every day, calculating the risk hierarchy of each merchant according to the offline historical risk data of the previous day, and calculating the video acquisition parameter set of the merchant on the current day. Specifically, the first task includes generating a video acquisition table in a first task period according to a video acquisition parameter set of a merchant and an execution period of the first task; the video acquisition table comprises acquisition time of each merchant in a first task period; correspondingly, the second task includes determining a current acquisition merchant currently performing kitchen video data acquisition according to the video acquisition parameter set, including: and the second task queries the merchant with the acquisition time matched with the current time from the video acquisition table as the current acquisition merchant.

In a preferred mode, the first task includes determining a configuration parameter set matched with a merchant and a risk layering parameter set matched with a risk level of the merchant to which the merchant belongs, and determining a video acquisition parameter set corresponding to the merchant according to the configuration parameter set and the risk layering parameter set, and specifically includes: determining the risk level of each merchant according to the historical abnormal data, and acquiring a risk layering parameter set matched with the risk level of each merchant; taking the parameter set with the shortest acquisition period in the configuration parameter set and the risk wind acquisition parameter set as the video acquisition parameter set; storing the video acquisition parameter set of the commercial tenant to a message area corresponding to the acquisition period; the second task includes determining a current acquisition merchant currently performing kitchen video data acquisition according to the video acquisition parameter set, and acquiring kitchen video data of the current acquisition merchant from a kitchen video source, and specifically includes: acquiring a current acquisition merchant from a message area corresponding to the acquisition period according to the acquisition period; and acquiring the kitchen video data of the current acquisition merchant from the kitchen video source path according to the video acquisition parameter set indication of the current acquisition merchant.

Of course, the function of capturing kitchen video data may be decoupled into two steps of capturing and capturing, which are respectively performed by the second task and the third task. Specific: starting a third task, wherein the third task and the second task are executed asynchronously to realize that kitchen video data of the current acquisition merchant are acquired from a kitchen video source; correspondingly, the second task includes determining a current acquisition merchant currently performing kitchen video data acquisition according to the video acquisition parameter set, acquiring kitchen video data of the current acquisition merchant from a kitchen video source, and includes: the second task adds the information of the current acquisition merchant to an acquisition queue or to a time chain according to the acquisition time of each merchant in the video acquisition table; and the third task comprises reading the message node from the collection queue or the time chain, and collecting kitchen video data of the current collection merchant from a kitchen video source according to the current collection merchant corresponding to the message node.

Specifically, the collecting kitchen video data of the current collecting merchant from the kitchen video source includes: acquiring sampling time length according to the video acquisition parameter set; determining an initial kitchen video of the current time corresponding to the current acquisition merchant from the kitchen video source; identifying a key frame containing foreground information from the initial kitchen video, and intercepting kitchen video data from the key frame to the time length indicated by the sampling duration as the kitchen video data collected at this time; or, performing frame extraction from the initial kitchen video according to a preset frame extraction parameter set to obtain kitchen video data with sampling duration indicating time length, wherein the preset frame extraction parameter set at least comprises frame extraction frequency set based on sampling time and/or sampling area. Preferably, the frame extraction logic further comprises an instruction for judging the shielding of the camera equipment, and if the camera equipment is determined to be shielded or shielded for a certain duration or a plurality of times, shielding early warning information is generated and notified to the corresponding merchant.

In this embodiment, the method further includes identifying the collected kitchen video data, specifically: initiating a fifth task for identifying kitchen video data; the fifth task includes, for the collected kitchen video data, identifying a video frame including an abnormal picture and saving the video frame as a food safety risk video; if the food security risk video corresponds to the night peak period, pest identification is carried out on video data of a risk merchant corresponding to the food security risk video in the night peak period, first early warning information for indicating environmental sanitation problems is generated and sent to the risk merchant; if the food security risk video corresponds to a food production peak period, identifying operation abnormality and/or producer dressing abnormality in a production flow, generating second early warning information for indicating the production flow abnormality, and sending the second early warning information to the risk merchant; if the food security risk video corresponds to the food taking area, identifying abnormal food taking flow, storing the abnormal food taking flow and an order of a corresponding period in a correlated manner, generating third early warning information for indicating the abnormal food taking flow, and sending the third early warning information to the risk merchant.

Further, if the kitchen video data corresponds to a key area such as a preliminary meal preparation area (including raw material cleaning, preparation, etc.), a preparation area, a food preparation circulation area, a food preparation packaging area, a food preparation tool and tableware cleaning and disinfecting area, a food preparation tool and tableware preservation area, etc., identifying targets in a video frame includes but is not limited to: insect pests such as flies, staff dressing (such as a main kitchen and a kitchen) for executing different working tasks, and the like. If the kitchen video data corresponds to a raw material acceptance area, a raw material storage area, objects in the video frame are identified including, but not limited to, mice, cockroaches, and the like. If the kitchen video data corresponds to a rush hour period, then objects in the video frame are identified including, but not limited to, mice, cockroaches, and the like. Tracking a target, and judging pest emergence condition and distribution data if the target is matched with the upper pests; if the target matches with the worker, judging whether the worker wears the employee's card or not according to the dressing specification of the worker. And if the kitchen video data corresponds to the cooking bench and the food manufacturing process, identifying the material state of the spare meal. If the food risk is identified, an early warning prompt is sent to the merchant, so that the assisted catering platform timely finds food safety problems such as mess of the merchant, irregular operation and the like, and provides assisted business service value for the merchant.

Further, if the food security risk video corresponds to the food taking area, identifying whether the food taking process is abnormal, and storing video data containing the abnormality in association with the order and the occurrence time of the abnormality. It should be noted that, in the case of no conflict, the features given in the present embodiment and other embodiments of the present application may be combined with each other, and steps S101 and S102 or similar terms do not limit that the steps must be performed sequentially.

Therefore, the method provided by the embodiment is described, and the acquisition period can be specified through the configuration parameter set of the merchant and/or the risk layering parameter set corresponding to the risk level of the merchant, so that the problem of low effectiveness of kitchen acquisition data is at least partially solved. And the calculation of the video acquisition parameter set and the kitchen data acquisition are decoupled into different task execution, so that the processing efficiency can be improved. Further, the fourth task is used for adjusting the risk level of the commercial tenant, different risk layering parameter sets can be configured according to video acquisition requirements by different risk levels of the commercial tenant, and corresponding acquisition periods or acquisition frequencies are arranged in the risk layering parameter sets, so that automatic frequency raising or frequency lowering of the acquisition frequencies is realized, the effectiveness of kitchen data acquisition is improved, and the consumption of hardware resources is reduced.

In correspondence with the first embodiment, a second embodiment of the present application provides a kitchen data processing device, and relevant portions will be referred to in the description of the corresponding method embodiments. Referring to fig. 4, there is shown a kitchen data processing apparatus comprising: a task starting unit 401, configured to start a first task for determining a video acquisition parameter set, where the first task is used to determine a video acquisition parameter set corresponding to a merchant that is to acquire kitchen video data; the parameter set calculating unit 402 is configured to determine a configuration parameter set matched with a merchant and a risk layering parameter set matched with a risk level of the merchant to which the merchant belongs, and determine a video acquisition parameter set corresponding to the merchant according to the configuration parameter set and the risk layering parameter set; wherein the video acquisition parameter set at least indicates the acquisition period of kitchen video data of a merchant matching the corresponding parameter set; and the acquisition unit 403 is configured to initiate a second task for acquiring kitchen video data, where the second task includes determining, according to the video acquisition parameter set, a current acquisition merchant currently performing kitchen video data acquisition, and acquiring kitchen video data of the current acquisition merchant from a kitchen video source.

Optionally, the parameter set calculating unit 402 is specifically configured to: the first task includes obtaining a rush hour parameter set configured for a rush hour period; determining a parameter set with the shortest acquisition period as a video acquisition parameter set of the merchant according to the peak period parameter set, the configuration parameter set and the risk layering parameter set; or taking the parameter set with the highest priority among the peak period parameter set, the configuration parameter set and the risk layering parameter set as the video acquisition parameter set of the merchant.

Optionally, the parameter set calculating unit 402 is specifically configured to: the first task includes obtaining a global parameter set, and using the global parameter set as a video acquisition parameter set of a merchant not matching any parameter set of the upper configuration parameter set, the risk stratification parameter set and the peak period parameter set: and/or, the first task comprises determining that the acquisition time for kitchen video data acquisition matches with a rush hour period and successfully acquiring a rush hour parameter set, and taking the rush hour parameter set as the video acquisition parameter set of the merchant at the acquisition time.

Optionally, the parameter set calculating unit 402 is specifically configured to: the first task comprises carrying out peak period parameter set matching aiming at a merchant, and if the acquisition time of the merchant for kitchen video data acquisition is determined to be not matched with the peak period or the peak period parameter set is not successfully acquired, determining whether the merchant is matched with a valid configuration parameter set and/or risk layering parameter set; if the merchant is not matched with any effective configuration parameter set and/or risk layering parameter set, taking the global parameter set as a video acquisition parameter set of the merchant; the first task further comprises, for a risk-free merchant with a risk level of the merchant, if the current matching peak period is determined and a peak period parameter set is acquired, taking the peak period parameter set as a video acquisition parameter set of the risk-free merchant; if the current unmatched peak period or the unsuccessfully acquired peak period parameter set is determined, acquiring a matched configuration parameter set of each risk-free merchant as a video acquisition parameter set of the corresponding merchant; and if the configuration parameter set is not successfully acquired, taking the global parameter set as a video acquisition parameter set of the risk-free merchant.

Optionally, the configuration parameter set includes: a regional parameter set configured for the designated region and/or a merchant list parameter set configured for the designated merchant; the parameter set calculating unit 402 is specifically configured to: determining whether the merchant hits the regional parameter set according to regional information corresponding to the merchant, and if so, taking the regional parameter set as a configuration parameter set matched with the merchant; and/or determining whether the merchant hits the merchant list parameter set according to the merchant name of the merchant, if so, taking the merchant list parameter set as the matched configuration parameter set of the merchant; and if the matched configuration parameter set of the merchant comprises a regional parameter set and a merchant list parameter set, taking the parameter set with a shorter sampling period as the video acquisition parameter set of the merchant, or taking the parameter set with a higher priority as the video acquisition parameter set of the merchant.

Optionally, the parameter set calculating unit 402 is specifically configured to: determining the risk level of each merchant according to the historical abnormal data, and acquiring a risk layering parameter set matched with the risk level of each merchant; taking the parameter set with the shortest acquisition period in the configuration parameter set and the risk wind acquisition parameter set as the video acquisition parameter set; storing the video acquisition parameter set of the commercial tenant to a message area corresponding to the acquisition period; the acquisition unit 403 is specifically configured to: acquiring a current acquisition merchant from a message area corresponding to the acquisition period according to the acquisition period; and acquiring the kitchen video data of the current acquisition merchant from the kitchen video source path according to the video acquisition parameter set indication of the current acquisition merchant.

Optionally, the first task is a timing task; the acquisition unit 403 is specifically configured to: the first task comprises the step of generating a video acquisition table in a first task period according to a video acquisition parameter set of a merchant and an execution period of the first task; the video acquisition table comprises acquisition time of each merchant in a first task period; the second task comprises inquiring a merchant with the acquisition time matched with the current time from the video acquisition table as the current acquisition merchant.

Optionally, the collecting unit 403 is specifically configured to: starting a third task, wherein the third task and the second task are executed asynchronously to realize that kitchen video data of the current acquisition merchant are acquired from a kitchen video source; the second task comprises adding the information of the current acquisition merchant to an acquisition queue or a time chain according to the acquisition time of each merchant in the video acquisition table; and the third task comprises reading the message node from the collection queue or the time chain, and collecting kitchen video data of the current collection merchant from a kitchen video source according to the current collection merchant corresponding to the message node.

Optionally, the device further includes an automatic acquisition cycle adjustment unit, where the automatic acquisition cycle adjustment unit is configured to: starting a fourth task for adjusting the risk level of the merchant to which the merchant belongs; the fourth task is a timing task and is executed asynchronously with the first task; the fourth task comprises the steps of obtaining historical abnormal data of a merchant, and dividing the merchant into risk-free merchants if abnormal data does not exist in a first specified number of continuous time periods; if there is abnormal data for each time period within a first specified number of consecutive time periods, classifying the merchant into a first risk level; dividing the merchant into a second risk level if there is anomalous data within a first specified number of consecutive time periods and the anomalous data is within a second specified number of consecutive time periods; if there is abnormal data in the first specified number of consecutive time periods and the abnormal data is in the third specified time period, dividing the merchant into a third risk level; the first specified number of consecutive time periods includes the second specified number of consecutive time periods and the third specified time period; receiving a set of merchant risk levels for specified merchants, the specified merchants identified as specified risk merchants with specified risk levels; the fourth task includes eliminating the specified risk merchant when the merchant risk level to which the merchant belongs is adjusted so as to maintain the merchant risk level configured for the specified risk merchant.

Optionally, the collecting unit 403 is specifically configured to: acquiring sampling time length according to the video acquisition parameter set; determining an initial kitchen video of the current time corresponding to the current acquisition merchant from the kitchen video source; identifying a key frame containing foreground information from the initial kitchen video, and intercepting kitchen video data from the key frame to the time length indicated by the sampling duration as the kitchen video data collected at this time; or, performing frame extraction from the initial kitchen video according to a preset frame extraction parameter set to obtain kitchen video data with sampling duration indicating time length, wherein the preset frame extraction parameter set at least comprises frame extraction frequency set based on sampling time and/or sampling area.

Optionally, the collecting unit 403 is specifically configured to: initiating a fifth task for identifying kitchen video data; the fifth task includes, for the collected kitchen video data, identifying a video frame including an abnormal picture and saving the video frame as a food safety risk video; if the food security risk video corresponds to the night peak period, pest identification is carried out on video data of a risk merchant corresponding to the food security risk video in the night peak period, first early warning information for indicating environmental sanitation problems is generated and sent to the risk merchant; if the food security risk video corresponds to a food production peak period, identifying operation abnormality and/or producer dressing abnormality in a production flow, generating second early warning information for indicating the production flow abnormality, and sending the second early warning information to the risk merchant; if the food security risk video corresponds to the food taking area, identifying abnormal food taking flow, storing the abnormal food taking flow and an order of a corresponding period in a correlated manner, generating third early warning information for indicating the abnormal food taking flow, and sending the third early warning information to the risk merchant.

Optionally, the apparatus further includes a configuration unit, where the configuration unit is configured to: receiving configuration information aiming at a configuration parameter set and/or a risk layering parameter set, wherein the configuration information comprises sampling periods and/or parameter set priorities indicated by the corresponding parameter sets; checking whether the time length sequence of the sampling periods of different parameter sets accords with a preset standard sequence or not according to the configuration information, and if not, generating prompt information that the sampling periods are inconsistent with the preset standard sequence; and/or checking whether the parameter set priorities of different parameter sets accord with a preset priority order aiming at the configuration information, if not, generating prompt information of which the priorities are inconsistent with the preset priority order; and validating the configuration information in response to confirming the continued configuration for the prompt information.

Based on the foregoing embodiments, a third embodiment of the present application provides an electronic device, and relevant portions may be referred to the corresponding descriptions of the foregoing embodiments. Referring to fig. 5, an electronic device is shown, which includes: a memory, and a processor; the memory is used for storing a computer program, and the computer program is executed by the processor to execute the method provided by the embodiment of the application.

Based on the foregoing embodiments, a fourth embodiment of the present application provides a computer storage medium, and relevant portions may be referred to the corresponding descriptions of the foregoing embodiments. The schematic diagram of the computer storage medium is similar to the schematic diagram of the electronic device, and the memory in the figure can be understood as the storage medium. The computer storage medium stores computer-executable instructions that, when executed by a processor, are configured to implement the methods provided by embodiments of the present application.

It should be noted that, in the embodiments of the present application, the situations of platform operation, order transaction and the like may be involved, and in practical application, the solution described herein should be applied within the scope allowed by the applicable legal regulations in the country where the applicable legal regulations are met. It should be noted that, in the embodiments of the present application, the use of user data may be involved, and in practical applications, user specific personal data should be used in the schemes described herein within the scope allowed by applicable legal regulations in the country where the requirements of applicable legal regulations are met (for example, the user explicitly agrees, and the user is informed practically, etc.).

In one typical configuration, the electronic device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

While the preferred embodiment has been described, it is not intended to limit the invention thereto, and any person skilled in the art may make variations and modifications without departing from the spirit and scope of the present invention, so that the scope of the present invention shall be defined by the claims of the present application.

Claims

1. A kitchen data processing method, comprising:

starting a first task for determining a video acquisition parameter set, wherein the first task is used for determining the video acquisition parameter set corresponding to a merchant of kitchen video data to be acquired;

the first task comprises determining a configuration parameter set matched with a merchant and a risk layering parameter set matched with a risk level of the merchant to which the merchant belongs, and determining a video acquisition parameter set corresponding to the merchant according to the configuration parameter set and the risk layering parameter set; wherein the video acquisition parameter set at least indicates the acquisition period of kitchen video data of a merchant matching the corresponding parameter set;

and starting a second task for acquiring kitchen video data, wherein the second task comprises the steps of determining a current acquisition merchant for acquiring the kitchen video data according to the video acquisition parameter set, and acquiring the kitchen video data of the current acquisition merchant from a kitchen video source.

2. The method as recited in claim 1, further comprising:

the first task includes obtaining a rush hour parameter set configured for a rush hour period;

the determining the video acquisition parameter set corresponding to the merchant according to the configuration parameter set and the risk stratification parameter set comprises the following steps:

Determining a parameter set with the shortest acquisition period as a video acquisition parameter set of the merchant according to the peak period parameter set, the configuration parameter set and the risk layering parameter set; or,

and taking the parameter set with the highest priority in the peak period parameter set, the configuration parameter set and the risk layering parameter set as the video acquisition parameter set of the merchant.

3. The method as recited in claim 2, further comprising:

the first task includes obtaining a global parameter set, and using the global parameter set as a video acquisition parameter set of a merchant not matching any parameter set of the upper configuration parameter set, the risk stratification parameter set and the peak period parameter set: and/or the number of the groups of groups,

the first task comprises the steps of determining that the acquisition time for kitchen video data acquisition is matched with a rush hour period and successfully acquiring a rush hour parameter set, and taking the rush hour parameter set as a video acquisition parameter set of the merchant at the acquisition time.

4. The method as recited in claim 1, further comprising:

the first task comprises carrying out peak period parameter set matching aiming at a merchant, and if the acquisition time of the merchant for kitchen video data acquisition is determined to be not matched with the peak period or the peak period parameter set is not successfully acquired, determining whether the merchant is matched with a valid configuration parameter set and/or risk layering parameter set; if the merchant is not matched with any effective configuration parameter set and/or risk layering parameter set, taking the global parameter set as a video acquisition parameter set of the merchant;

The method further comprises the steps of:

the first task comprises, for a risk-free merchant with a risk level of the merchant, taking the peak period parameter set as a video acquisition parameter set of the risk-free merchant if the peak period parameter set is determined to be matched with the peak period currently and the peak period parameter set is acquired; if the current unmatched peak period or the unsuccessfully acquired peak period parameter set is determined, acquiring a matched configuration parameter set of each risk-free merchant as a video acquisition parameter set of the corresponding merchant; and if the configuration parameter set is not successfully acquired, taking the global parameter set as a video acquisition parameter set of the risk-free merchant.

5. The method of claim 1, wherein the set of configuration parameters comprises: a regional parameter set configured for the designated region and/or a merchant list parameter set configured for the designated merchant;

the determining the matched configuration parameter set of the merchant includes:

determining whether the merchant hits the regional parameter set according to regional information corresponding to the merchant, and if so, taking the regional parameter set as a configuration parameter set matched with the merchant; and/or determining whether the merchant hits the merchant list parameter set according to the merchant name of the merchant, if so, taking the merchant list parameter set as the matched configuration parameter set of the merchant;

And if the matched configuration parameter set of the merchant comprises a regional parameter set and a merchant list parameter set, taking the parameter set with a shorter sampling period as the video acquisition parameter set of the merchant, or taking the parameter set with a higher priority as the video acquisition parameter set of the merchant.

6. The method of claim 1, wherein the determining a configuration parameter set matched by a merchant and a risk stratification parameter set matched by a risk level of the merchant to which the merchant belongs, and determining a video acquisition parameter set corresponding to the merchant according to the configuration parameter set and the risk stratification parameter set, comprises:

determining the risk level of each merchant according to the historical abnormal data, and acquiring a risk layering parameter set matched with the risk level of each merchant;

taking the parameter set with the shortest acquisition period in the configuration parameter set and the risk wind acquisition parameter set as the video acquisition parameter set;

storing the video acquisition parameter set of the commercial tenant to a message area corresponding to the acquisition period;

the determining, according to the video collection parameter set, a current collection merchant that performs kitchen video data collection currently, and collecting kitchen video data of the current collection merchant from a kitchen video source, includes:

Acquiring a current acquisition merchant from a message area corresponding to the acquisition period according to the acquisition period;

and acquiring the kitchen video data of the current acquisition merchant from the kitchen video source path according to the video acquisition parameter set indication of the current acquisition merchant.

7. The method as recited in claim 1, further comprising:

the first task is a timing task;

the first task comprises the step of generating a video acquisition table in a first task period according to a video acquisition parameter set of a merchant and an execution period of the first task; the video acquisition table comprises acquisition time of each merchant in a first task period;

the second task includes determining a current acquisition merchant currently performing kitchen video data acquisition according to the video acquisition parameter set, including:

and the second task queries the merchant with the acquisition time matched with the current time from the video acquisition table as the current acquisition merchant.

8. The method of claim 7, wherein the method further comprises:

starting a third task, wherein the third task and the second task are executed asynchronously to realize that kitchen video data of the current acquisition merchant are acquired from a kitchen video source;

The second task includes determining a current acquisition merchant currently performing kitchen video data acquisition according to the video acquisition parameter set, acquiring kitchen video data of the current acquisition merchant from a kitchen video source, including:

the second task adds the information of the current acquisition merchant to an acquisition queue or to a time chain according to the acquisition time of each merchant in the video acquisition table;

and the third task comprises reading the message node from the collection queue or the time chain, and collecting kitchen video data of the current collection merchant from a kitchen video source according to the current collection merchant corresponding to the message node.

9. The method as recited in claim 1, further comprising:

starting a fourth task for adjusting the risk level of the merchant to which the merchant belongs; the fourth task is a timing task and is executed asynchronously with the first task;

the fourth task comprises the steps of obtaining historical abnormal data of a merchant and determining a merchant risk level to which the merchant belongs according to the historical abnormal data;

wherein the determining, according to the historical abnormal data, the merchant risk level to which the merchant belongs includes:

If no abnormal data exists in a first specified number of continuous time periods, dividing the merchant into risk-free merchants; if there is abnormal data for each time period within a first specified number of consecutive time periods, classifying the merchant into a first risk level;

dividing the merchant into a second risk level if there is anomalous data within a first specified number of consecutive time periods and the anomalous data is within a second specified number of consecutive time periods;

if there is abnormal data in the first specified number of consecutive time periods and the abnormal data is in the third specified time period, dividing the merchant into a third risk level;

the first specified number of consecutive time periods includes the second specified number of consecutive time periods and the third specified time period;

wherein the method further comprises:

receiving a set of merchant risk levels for specified merchants, the specified merchants identified as specified risk merchants with specified risk levels;

the fourth task includes eliminating the specified risk merchant when the merchant risk level to which the merchant belongs is adjusted so as to maintain the merchant risk level configured for the specified risk merchant.

10. The method of claim 1, wherein the capturing kitchen video data of the currently captured merchant from a kitchen video source comprises:

acquiring sampling time length according to the video acquisition parameter set;

determining an initial kitchen video of the current time corresponding to the current acquisition merchant from the kitchen video source;

identifying a key frame containing foreground information from the initial kitchen video, and intercepting kitchen video data from the key frame to the time length indicated by the sampling duration as the kitchen video data collected at this time; or,

and extracting frames from the initial kitchen video according to a preset frame extraction parameter set to obtain kitchen video data with sampling duration indicating time length, wherein the preset frame extraction parameter set at least comprises frame extraction frequency set based on sampling time and/or sampling area.

11. The method as recited in claim 1, further comprising:

initiating a fifth task for identifying kitchen video data;

the fifth task includes, for the collected kitchen video data, identifying a video frame including an abnormal picture and saving the video frame as a food safety risk video;

if the food security risk video corresponds to the night peak period, pest identification is carried out on video data of a risk merchant corresponding to the food security risk video in the night peak period, first early warning information for indicating environmental sanitation problems is generated and sent to the risk merchant;

If the food security risk video corresponds to a food production peak period, identifying operation abnormality and/or producer dressing abnormality in a production flow, generating second early warning information for indicating the production flow abnormality, and sending the second early warning information to the risk merchant;

if the food security risk video corresponds to the food taking area, identifying abnormal food taking flow, storing the abnormal food taking flow and an order of a corresponding period in a correlated manner, generating third early warning information for indicating the abnormal food taking flow, and sending the third early warning information to the risk merchant.

12. The method as recited in claim 1, further comprising:

receiving configuration information aiming at a configuration parameter set and/or a risk layering parameter set, wherein the configuration information comprises sampling periods and/or parameter set priorities indicated by the corresponding parameter sets;

checking whether the time length sequence of the sampling periods of different parameter sets accords with a preset standard sequence or not according to the configuration information, and if not, generating prompt information that the sampling periods are inconsistent with the preset standard sequence; and/or the number of the groups of groups,

checking whether the priority of parameter sets of different parameter sets accords with a preset priority order or not according to the configuration information, and if not, generating prompt information of which the priority is inconsistent with the preset priority order;

And validating the configuration information in response to confirming the continued configuration for the prompt information.

13. An electronic device, comprising:

a memory, and a processor; the memory is adapted to store a computer program which, when executed by the processor, performs the method of any of claims 1-12.