Systems, methods, and computer readable media for food safety

Abstract

Systems, methods, and computer-readable media for food safety are disclosed. The system comprises one or more data sources and a server connected to a network. The data source includes one or more sensors located at the food enterprise and connected to a network. The data source is configured to: track one or more events at a food enterprise; and generating data related to food safety risk and hygiene compliance tracking based on the one or more events. The server comprises: a data collection module configured to collect data from one or more data sources via a network; a database interaction module configured to store the data collected by the data collection module into a database and retrieve the data from the database; and a predictive analysis module configured to analyze the data in the database using a predictive analysis algorithm to identify one or more trends and one or more predictive indicators, and calculate a probability of causing a future examination violating health regulations based on the analyzed data.

Description

[0001] This application is a divisional application of patent application No. 201980031127.0, filed on May 16, 2019, entitled "Food Safety Risk and Hygiene Compliance Tracking". Technical Field

[0002] This disclosure generally addresses food safety and hygiene risks, as well as compliance systems and methods. Background Technology

[0003] Currently, many food businesses (e.g., restaurants, meat processing plants, grocery stores, etc.) use manual processes to track their compliance with various health regulations at the county, state, and federal levels. For example, some food businesses conduct regular (e.g., monthly) self-audits, during which one or more people check whether the food business is in compliance with health regulations. After completing the self-audit, the food business's management may receive a compliance "score" and / or audit report detailing the food business's status and how those statuses pass or fail the relevant health regulations.

[0004] A “self-audit” is a series of questions that may relate to one or more departments / regions within a food business. Each question may also be associated with one or more sections of health regulations relevant to that question. The answer to each question may result in zero or more “findations.” In one embodiment, there is no upper limit to the number of possible findings for a given question. Findings may be of one of two types: a “serious” finding, which indicates a violation of health regulations serious enough to necessitate the closure of the food business; and a “recommended practice” finding, which indicates a violation of health regulations that does not require the closure of the food business but necessitates its rectification.

[0005] While these "self-audits" can provide useful insights into past health compliance issues, they cannot help food companies predict the probability of future health regulation violations. However, analyzing data integrated from 1) self-audit data, 2) health department inspection data, and 3) sensor data from the food company's environment can be used to calculate the probability of future health regulation violations by the food company. Summary of the Invention

[0006] The embodiments disclosed herein can analyze data and output information from various sources, providing insights into specific risk factors in a way that helps in taking targeted measures to address such risk factors. Thus, the embodiments disclosed herein can allow users to proactively reduce risks related to food safety and hygiene. Furthermore, the embodiments disclosed herein can allow users to allocate limited resources to specific risk factors that are most likely to lead to the greatest reduction in overall food safety and hygiene risk.

[0007] An exemplary embodiment includes a food safety risk system. This system embodiment includes a server connected to a network. The server includes a data collection module, a database interaction module, and a predictive analytics module. The data collection module is configured to collect data via the network from one or more data sources relating to food safety risks and hygiene compliance tracking of food businesses. The database interaction module is configured to store the data collected by the data collection module into a database and retrieve data from the database. The predictive analytics module is configured to analyze the data in the database and, based on the analyzed data, calculate the probability that the food business has violated health regulations.

[0008] In another embodiment, the one or more data sources include at least one of the following: sensor data from one or more sensors of the food enterprise, dispenser data from one or more dispensers of the food enterprise, pest control data, health department inspection data, self-audit data, self-reporting data, and equipment maintenance and upkeep data.

[0009] In another embodiment, the one or more sensors of the food company include at least one of the following: a thermometer, a hygrometer, and a barometer.

[0010] In another embodiment, the one or more dispensers include at least one of the following: a disinfectant dispenser and a water dispenser.

[0011] In another embodiment, when the calculated probability of a food company violating health regulations exceeds a threshold, the server sends a notification to one or more devices associated with the food company.

[0012] In another embodiment, the server also includes a report generation module. The report generation module is configured to generate reports that include the probability of food businesses violating health regulations. In some such instances, the report generator is configured to send the report to a client device for display.

[0013] In the above system embodiments, the probability of a food company violating health regulations can include a predicted risk score for the food company. For example, the probability of a food company violating health regulations can include a predicted risk score and multiple individual risk indicators for the food company. Each of these multiple individual risk indicators can provide a risk assessment relative to other food companies. Examples that can be included as multiple individual risk indicators for a food company include personal hygiene, cleanliness and sanitation, time and temperature, and documentation. Other examples that can be included as multiple individual risk indicators for a food company include cross-contamination, pest control, date stamping, and other or a variety of other data.

[0014] The document also disclosed the purpose of Shanghai's system for tracking food safety risks and hygiene compliance.

[0015] Another exemplary embodiment includes a method implemented on at least one server connected to a network. This method embodiment may include the steps of: collecting data via the network from one or more data sources, the data relating to food safety risks and hygiene compliance tracking of a food enterprise. The method may further include the steps of: storing the collected data in a database; retrieving data from the database; analyzing the data in the database; and calculating the probability of the food enterprise violating health regulations based on the analyzed data.

[0016] In another embodiment, the one or more data sources include at least one of the following: sensor data from one or more sensors of the food enterprise, dispenser data from one or more dispensers of the food enterprise, pest control data, health department inspection data, self-audit data, self-reporting data, and equipment maintenance and upkeep data.

[0017] In another embodiment, the one or more sensors of the food company include at least one of the following: a thermometer, a hygrometer, and a barometer.

[0018] In another embodiment, the one or more dispensers include at least one of the following: a disinfectant dispenser and a water dispenser.

[0019] In another embodiment, when the calculated probability of a food company violating health regulations exceeds a threshold, the server sends a notification to one or more devices associated with the food company.

[0020] In another embodiment, the method may include the step of generating a report that includes the probability that a food business has violated health regulations. This additional embodiment may also include the step of sending the report to a client device for display.

[0021] In the above method embodiments, the probability of a food company violating health regulations may include a predicted risk score for the food company. For example, the probability of a food company violating health regulations may include a predicted risk score and multiple individual risk indicators for the food company. Each of these multiple individual risk indicators can provide a risk assessment relative to other food companies. Examples that may be included as multiple individual risk indicators for a food company include personal hygiene, cleanliness and sanitation, time and temperature, and documentation. Other examples that may be included as multiple individual risk indicators for a food company include cross-contamination, pest control, date stamping, and other or a variety of other data.

[0022] Another embodiment includes a non-transitory computer-readable medium comprising instructions. When executed by a computer, these instructions cause the computer to collect data over a network from one or more data sources relating to food safety risks and hygiene compliance tracking for a food business. When executed by a computer, these instructions may also cause the computer to store the collected data in a database, retrieve data from the database, analyze the data in the database, and calculate the probability of the food business violating health regulations based on the analyzed data.

[0023] In another embodiment, the one or more data sources include at least one of the following: sensor data from one or more sensors of the food enterprise, dispenser data from one or more dispensers of the food enterprise, pest control data, health department inspection data, self-audit data, self-reporting data, and equipment maintenance and upkeep data.

[0024] In another embodiment, the one or more sensors of the food company include at least one of the following: a thermometer, a hygrometer, and a barometer.

[0025] In another embodiment, the one or more dispensers include at least one of the following: a disinfectant dispenser and a water dispenser.

[0026] In another embodiment, the non-transitory computer-readable medium further includes instructions that, when executed by a computer, cause the computer to: send a notification to one or more devices associated with the food company when the calculated probability that the food company has violated health regulations exceeds a threshold.

[0027] In another embodiment, when executed by a computer, the above instructions can also cause the computer to generate a report that includes the probability that a food company has violated health regulations. These instructions, when executed by a computer, may also cause the computer to transmit the report to a client device for display.

[0028] In the above embodiments of the non-transitory computer-readable medium including instructions, the instructions, when executed by a computer, can cause the computer to calculate the probability of a food company violating health regulations, including a predicted risk score for the food company. For example, the probability of a food company violating health regulations can be calculated to include a predicted risk score for the food company and multiple individual risk indicators for the food company. Each of the multiple individual risk indicators for the food company can be calculated to provide a risk assessment relative to other food companies. Examples of multiple individual risk indicators that can be calculated for a food company include personal hygiene, cleanliness and hygiene, time and temperature, and documentation. Other examples that can be included as multiple individual risk indicators for a food company include cross-contamination, pest control, date stamping, and other or a wide variety of other data. Attached Figure Description

[0029] The accompanying drawings illustrate specific embodiments of the invention and therefore do not limit the scope of the invention. The drawings are intended to be used in conjunction with the explanations in the following description. Embodiments of the invention will now be described with reference to the accompanying drawings, wherein the same numerals denote the same elements.

[0030] Figure 1 A system for tracking food safety risks and hygiene compliance, according to an example embodiment, is shown.

[0031] Figure 2 Various modules that can be executed by a food safety risk and hygiene compliance tracking system according to an example embodiment are shown.

[0032] Figure 3 The information flow through a food safety risk and hygiene compliance tracking system according to an example embodiment is shown.

[0033] Figure 4A A report for a food company is shown according to an example embodiment.

[0034] Figure 4B and Figure 4C Another report for a food company is shown, based on an example embodiment. Figure 4B The overall customer report is shown, while Figure 4C This shows some aspects of the report for the selected customer stores.

[0035] Figure 5 This is a block diagram illustrating an example machine on which any one or more example embodiments can be implemented. Detailed Implementation

[0036] The following detailed description is exemplary in nature and is not intended to limit the scope, applicability, or configuration of the invention in any way. In fact, the following description provides some practical illustrations for carrying out exemplary embodiments of the invention. Examples of structure, materials, and / or dimensions are provided for selected elements. Those skilled in the art will recognize that many of the examples mentioned have various suitable alternatives.

[0037] A comprehensive food safety and hygiene risk and compliance system is disclosed. In one embodiment, data from various sources is integrated into a database (or data store). Data sources may include one or more of the following: self-audits (e.g., performed by the food company itself or a third party), pest control services, hygiene department inspections, distribution equipment monitoring hygiene compliance, and various sensors within and / or near the food company. The data is analyzed to calculate the probability that the food company will violate health regulations in the future. Various preventative measures can then be implemented in response to the calculated probability.

[0038] The components of this system may include:

[0039] 1) Customer self-audit / data collection and task management tools,

[0040] 2) A data warehouse that integrates data feeds from different systems (e.g., customer self-audit utility data, pest control service data, food safety audit data, health department inspection data, and distribution equipment for monitoring health compliance).

[0041] 3) Alarm system, which issues an alarm when certain risk factors are identified.

[0042] 4) Client portal for reporting data, insights, and training.

[0043] 5) Mobile applications,

[0044] 6) Sensors are used to detect various operating / environmental conditions, and

[0045] 5) Includes an analysis module for predictive analysis algorithms.

[0046] These combined solutions will enhance our understanding of the risk factors and root causes of foodborne disease vectors and help clients mitigate such risks more proactively. The platform can be customized for multiple food safety market sectors. Furthermore, it can be tailored for any business that requires a large number of remote site personnel to collect data and leverage analytics from these diverse data sources.

[0047] Figure 1 A system 100 for tracking food safety risks and hygiene compliance, according to an example embodiment, is shown. The system may include a food company, one or more servers, one or more data stores, one or more client devices, and one or more interconnected networks (e.g., the Internet).

[0048] In one embodiment, the food business can be a retail store, fast food restaurant, hotel, delicatessen, bakery, etc. The food business may include one or more sensors and one or more dispensers (e.g., chemical dispensers). The one or more sensors may include one or more thermometers, hygrometers, barometers, etc. The one or more sensors can track and report one or more physical, chemical, and / or environmental conditions, such as temperature, pressure, humidity, etc. The one or more dispensers can track and report dispensing events, which may include the substance dispensed (e.g., liquid chemical compound, baking soda, water, etc.), the quantity dispensed, and a timestamp of the dispensing event. The system can use data from one or more dispensers to identify areas of risk and / or overuse, track human and utility usage, and identify and alert when critical problems occur and / or may occur.

[0049] In one embodiment, one or more data stores can store data from one or more sources, such as pest control data, health department inspection data, self-audit data, self-reporting data, equipment monitoring and maintenance data, etc. Combining multiple data sources helps improve the predictive ability of the system and the verification of its results.

[0050] In one embodiment, the mobile application allows users to input various types of data (e.g., answers to self-audit questions). For example, the mobile application can generate and present a list of tasks to be inspected, such as through user input on the mobile application, to guide the completion of the self-audit (e.g., by the food company itself or by a third party). In one embodiment, the mobile application displays one or more of the following: data generated by one or more sensors of the food company, data generated by one or more self-audits and / or health department inspections, and results of analyzing data related to the food company in a database. In one embodiment, a client portal is integrated into the mobile application. In one embodiment, customer self-audit / data collection and task management tools are integrated into the mobile application.

[0051] In one embodiment, the system can be used to determine whether automatically collected data differs from manually collected data. For example, if the automatically collected data differs significantly from manually collected data (e.g., self-audits or health department inspections), the system can send one or more alerts and / or notifications to inform one or more individual food businesses that there may be a problem with their sensors and / or dispensers.

[0052] Figure 2 Various modules that can be executed by a food safety risk and hygiene compliance tracking system, such as server 200 of system 100, according to an example embodiment are shown. For example, one or more servers can execute one or more of the following:

[0053] A data collection module that can receive data from one or more data sources;

[0054] The database interaction module can store the data collected by the data collection module into the database and retrieve data from the database as needed;

[0055] The predictive analytics module can analyze data in the database and calculate predictions based on the analyzed data;

[0056] The report generation module can generate reports based on data in the database and / or the results of the analysis module;

[0057] The customer portal module can be displayed on a personalized portal for each relevant food company;

[0058] The dashboard module can display a personalized dashboard for each relevant food business; and

[0059] Various other backend or server modules to enable the system to operate in the manner described.

[0060] Figure 3 The diagram illustrates the information flow 300 of a food safety risk and hygiene compliance tracking system 100 according to an example embodiment. Various data flows (e.g., self-audit data, data from external sources (e.g., health department data), resource and equipment data (e.g., from sensors and dispensers), and customer-provided data are analyzed by a predictive analytics module. The predictive analytics module identifies trends and predictive indicators. These trends and predictive indicators are used to develop action plans, which are communicated to various devices. Devices (and / or individuals using the devices) implement actions within the action plans, and the system tracks the implemented action plans to improve performance.

[0061] In one embodiment, the predictive analytics module assumes a correlation (e.g., a pseudo-linear relationship) between the number of findings generated by health department inspections and the probability that at least one of those findings is a "critical finding." Therefore, the predictive analytics module can use a Bayesian algorithm to calculate the probability of a health regulation violation.

[0062] As previously stated, each self-audit question may be associated with one or more sections of health regulations related to that question. In one embodiment, each combination of self-audit, self-audit question, and food business area can only have one unique finding. For example, a self-audit question may be related to personal hygiene and to four out of five departments in the store; therefore, during any given audit of the store, the question has four chances to lead to a finding. If only one finding of the question is recorded, then the probability that the question will lead to a finding in the store is 25% (1 / 4).

[0063] Continuing this example, if there are 5 self-assessment questions related to personal hygiene, and each of these 5 questions applies to one or more departments in the store, then summing up these 5 questions will yield 20 (4 departments x 5 questions) discovery opportunities. If only 1 discovery is recorded, the probability of discovery is 5% (1 / 20).

[0064] In one embodiment, the system collects data from all self-audits and health checks conducted by the food company and compares the self-audit data with the health check results. Using this analysis, the predictive analytics module can calculate the probability of future inspections leading to one or more findings for the food company in question.

[0065] The predictive analytics module can use a classifier to predict the probability of future health regulation violations. To train the classification model, health department inspection data is aggregated and fed into the model. When using the classification model to predict the probability of future health regulation violations, current data from various data streams is fed into the model. In one embodiment, risk factors for food businesses are weighted (e.g., risk factors A, B, and C may be insignificant individually, but together they indicate a significant food safety risk).

[0066] Data generated by a Health Department Inspection (“HDI”) (for each inspection) may include: the date of the inspection, the inspector’s name, the start and end times of the inspection, the name of the food business inspected, the geographical coordinates (e.g., longitude and latitude) of the inspected food business, the number of critical findings generated by the inspection, the number of recommended practice findings, one or more sections of health regulations related to the findings, and so on. In one embodiment, health compliance data is integrated into a database. Health compliance data can be generated from various sources, including chemical dispensers that convey data related to allocation events (e.g., the type and timestamp of the allocation event). In one embodiment, the chemical dispenser may communicate wirelessly. In one embodiment, the system executes an algorithm that interprets event data from the dispenser to determine compliance insights (e.g., store #1234 disinfected its floor for only 20 days in the last 30 days).

[0067] The importance of data from sensors and dispensers can vary. For example, if a thermometer reading on a coffee maker is too low, the coffee in the maker may spoil faster than if the temperature is within an acceptable range; however, if a thermometer measuring a roast chicken indicates that the cooked chicken is too low, the bacteria in the chicken may not have been sufficiently destroyed, potentially posing a food safety risk to the food company's customers.

[0068] In one embodiment, some individuals (e.g., field representatives of a service company) can access the system. For each food business, the system can notify one or more individuals of the food business's current risk score, the conditions that caused the current risk score, and a list of issues that, if resolved, could result in the largest possible reduction in the food business's current risk score.

[0069] It can generate reports that provide information on risk factors related to one or more customer stores. Figure 4A An example of such a report is shown. Figure 4B and 4C Another embodiment of this type of report is shown. Figure 4B The overall customer report is shown. Figure 4CThis illustrates certain aspects of the customer report for selected customer stores. For example, a food safety risk and hygiene compliance tracking system 100 can generate and display such a report, for example, at one or more client devices. In one instance, a predictive analytics module on the server can analyze data input into a database and calculate the probability of a store (e.g., a food business) violating health regulations based on the analyzed data, and a report generator module on the server can generate a report to be displayed on one or more client devices. For example, in this instance, the predictive analytics module on the server can analyze data input into a database and calculate a predicted risk score and a single risk indicator for each of the one or more stores, and the report generator module on the server can generate a report with the calculated predicted risk score and single risk indicator for each of the one or more stores to be displayed on one or more client devices.

[0070] Figure 4A A report 400 for a food company, according to an example embodiment, is shown. The report for the food company may include indications of whether data in one or more data streams shows a positive or negative trend. The report may include indications of whether the food company's risk is increasing, decreasing, or remaining unchanged. Figure 4A In the illustrated embodiment, information about store #304575 is shown. The “Current High-Risk Score” section of the report lists the store number, the current risk score for each store number, and an indication of whether the current risk score has increased, decreased, or remained unchanged compared to the previous report. Stores listed in the selected store's report can be associated with the selected store by geographical location, organizational structure, or some other connection.

[0071] In one embodiment, a food company's report may indicate its performance in one or more categories of health regulations. In another embodiment, a food company's report may indicate its performance in one or more categories of health regulations relative to other food companies belonging to the same organizational entity (e.g., brand, chain, corporation, division, etc.).

[0072] exist Figure 4A In the illustrated embodiment, the relative performance of a food company within each category (relative to other food companies) is represented by an arc. The arc length is inversely proportional to the relative performance of the food company within that category. In one embodiment, the color of the arc may indicate the relative performance of the food company within that category.

[0073] In one embodiment, a training program is tailored to risk factors identified in the food company's reports. The training program can be made available to the food company's employees through its client portal. In one embodiment, a link to the training program can be sent to the food company's employees when a triggering condition is detected (e.g., failure to clean the floor at the end of the day).

[0074] Figure 4B and Figure 4C A report 410 for a food business is shown according to another example embodiment. As described above, the food safety risk and hygiene compliance tracking system 100 can generate and display the report 410 at, for example, one or more client devices.

[0075] Report 410 includes a store selection panel 415. Store selection panel 415 can receive user input specifying one or more particular customer stores, and report 410 can generate additional information shown in report 410 based on the one or more customer stores (e.g., food businesses) specified at store selection panel 415. In the example shown, “All” stores are selected at store selection panel 415. Thus, the server of system 100 can retrieve input information related to the selected one or more stores from data storage at store selection panel 415, process the specified information, and generate report 410.

[0076] Report 410 also includes a risk category display 420. The risk category display 420 provides a breakdown of customer stores based on their predicted risk categories. As illustrated in the example here, the risk category display 420 divides customer stores into three categories, representing low, medium, and high predicted risk. Users can select any category from the risk category display 420, and after making such a selection, customer stores within the selected category can be displayed in report 410. In this way, the risk category display 420 allows users to view a subset of customer stores in isolation. For example, a user can select high-risk categories from the risk category display 420, and the report can then display detailed information about the customer stores in the high-risk categories. This allows users to selectively assess details related to stores in individual categories and allocate limited resources to addressing the risk in those categories.

[0077] Report 410 also includes a store risk panel 425. The store risk panel 425 may list specific customer stores 426, and for each specific customer store, list a predicted risk score 427 and a risk change indicator 428. As described elsewhere in this document, the predicted risk score 427 may be calculated based on various data input into the system and may represent the probability that a store (e.g., a food business) violates health regulations. The predicted risk score may represent the relative likelihood that an associated customer store will have more than a predetermined number of health check results if such an inspection were to be conducted currently. Thus, the higher the predicted risk score, the greater the likelihood that the associated customer store currently has more than a predetermined number of health check results. The risk change indicator may represent changes in the predicted risk score. The risk change indicator may specify (e.g., using up / down, side arrows, and / or red, green, or neutral colors) whether the predicted risk score of the associated customer store has increased, decreased, or remained unchanged over a preset past period (e.g., since the last report run, since the last inspection, the past month, a quarter, etc.). In the example shown here, report 410 may also include the total number of customer stores 429 that have experienced an increase in predicted risk scores, a decrease in predicted risk scores, and no change in predicted risk scores over a pre-defined period of time.

[0078] As shown here, report 410 may additionally include a risk indicator panel 430. The risk indicator panel may include multiple individual risk indicators 435. Each risk indicator 435 may provide a performance assessment for a customer store (e.g., a food business) within a specified food risk category, or, if selected, group customer stores. In some cases, each individual risk indicator 435 may represent the probability that a store (e.g., a food business) violates health regulations in the corresponding category of that individual risk indicator 435. In the illustrated example, there are risk indicators 435 for personal hygiene, cross-contamination, cleanliness and hygiene, time and temperature, pest control, date stamping, documentation, etc. Also in the illustrated embodiment, each risk indicator 435 may, for example, display the customer store's performance relative to other unselected customer stores or relative to predefined standards for each risk indicator, or, if selected, group customer stores. Here, each risk indicator 435 is represented by an arc and accompanied by a gauge placed at a position on the arc according to the performance of the specified risk indicator. The action may include along its distinguishable (e.g., color-coded, pattern-coded) sections, each of which corresponds to a different risk level that may be detected during a health check at the store.

[0079] Report 410 also includes an action section 440. Action section 440 can specify specific actions a user can take to reduce the predicted risk score 428 of a designated customer store or a group of designated customer stores. For example, if the personal hygiene risk indicator 435 is relatively high, action section 440 can specify specific actions that can be performed in the selected customer store (e.g., a sensor instructs a hand soap dispenser to be used five times per hour, but usage should be increased to ten times per hour depending on the number of people working in the store; training employees on handwashing procedures and frequency; increasing the frequency of self-checks) to reduce the personal hygiene risk indicator 435 and ultimately lower the overall predicted risk score 428. Report 410 can generate specific action items to be displayed in action section 440 based on instructions stored within the system described herein. Such instructions can, for example, include a specified action associated with each risk indicator in the report. In one embodiment, the action section may include a portion having one or more specific action items for a food business and another portion having one or more specific action items for someone outside the food business (e.g., a third-party service provider).

[0080] In some cases, including a geographic display 450 in report 410 may be useful. The geographic display 450 can show the location of the customer's stores and a relative indication of the predicted risk for each displayed store (e.g., color, shape, etc.). This can allow the report to convey whether stores in a particular risk category (e.g., high risk) are geographically concentrated, which may help in assessing remedies to reduce risk factors for such stores.

[0081] Figure 4C A report 410 is shown generated for a specific store (e.g., a food business) 426 selected by a user from the store risk panel 425. Once selected, the specific store 426 can be displayed isolated within the store risk panel 425. As shown here, the specifically selected store 426 has a risk change index 428 indicating that the predicted risk score 427 has increased over a predetermined period of time. The display of the total number of customer stores 429 can also be isolated from the specific selected store 426. In other instances, a user can select two or more stores from the store risk panel 425, and two additional stores of the specific selection can be displayed as described herein.

[0082] Selecting a specific store 426 allows report 410 to generate a risk indicator panel 430 for that specific store 426. In this example, the risk indicator panel 430 includes individual risk indicators 435, each showing the relative performance of the specific store 426 within a relevant category compared to other unselected stores. As seen here, the risk indicator panel 430 displays, in indicator categories such as time and temperature, date stamps, documents, etc., that the specific store 426 is operating at a high risk level (e.g., a risk detected during a health check) relative to the unselected stores. Thus, the risk indicator panel 430 for the specific store 426 can instruct the user to address these categories to reduce the predicted risk score 427 of the specific store 426.

[0083] Additionally, selecting a specific store 426 can cause report 410 to generate an action section 440 for that specific store 426. In one instance, action section 440 may display suggested action items for those indicator categories that will result in the maximum reduction of the predicted risk score 427. For example, for a specific store 426, action section 440 may display suggested action items for indicator categories such as time and temperature, date stamps, documents, etc.—those indicator categories that the specific store 426 is operating at a high-risk level (e.g., risk detected during a health check) relative to unselected stores.

[0084] Figures 4A-4C The predicted risk score is presented as a numerical value. In some instances, this value can be an absolute value indicating the probability that a predetermined number of findings will occur if a health check is performed at the current time. For example, in Figure 4A In this context, the predicted score is displayed as a percentage, which represents the estimated probability that a predetermined number of findings (e.g., two, three, four, five, etc.) will occur if a health check is performed at the current time.

[0085] Including the Predictive Risk Score 427 and the Risk Indicator Panel 430, users can individually identify which stores and risk indicator categories can be located via action items (e.g., shown in the Actions section 440) to view the risk of minimizing adverse health check results.

[0086] The system can use various techniques to process input data and output predicted risk scores and relative risk assessments for various risk indicator categories. As an example, numerous models can be generated and run based on the input data to simulate various outcomes. For instance, for each risk indicator category, multiple models can be run using input data associated with that category to simulate the results within that category. These results can be aggregated (e.g., averaged) to derive a result for each risk indicator category, which can then be compared to the results within that category for all other unselected stores to display the risk indicator for that category. Similarly, a store's predicted risk score can be generated by aggregating its risk indicator categories. For example, the risk indicator categories for a store can be averaged to provide its predicted risk score. In some cases, where certain applications of the system are considered to include risk indicator categories that are more likely to result in a higher risk profile for a store than other risk indicator categories, the risk indicator categories can be weighted when calculating this average.

[0087] In addition to the input data described earlier in this article, data related to the attributes of the store location can also be used as input data in the system. For example, in some instances, the data input into the system to generate risk indicator categories and predict risk scores may include one or more of the following: the population near the location, the income in the vicinity of the location, and the nearby tourist traffic.

[0088] As mentioned earlier, the system can send alerts to users. For example, the system's data storage may include a list of contact information associated with the store. In some cases, when the predicted risk score and / or one or more individual risk indicators change (e.g., increase) to a predetermined level, the system can output an alert based on the contact information associated with the store.

[0089] Figure 5 This is a block diagram illustrating an instance of machine 500, on which any one or more example embodiments can be implemented. In alternative embodiments, machine 500 may operate as a standalone device or may be connected (e.g., networked) to other machines. In a networked deployment, machine 500 may operate as a server machine, a client machine, or both in a client-server network environment. In one example, machine 500 may act as a peer machine in a peer-to-peer (P2P) (or other distributed) network environment. Machine 500 may implement or include Figure 1Any part of the system, apparatus, or method shown in -4 can be a computer, server, or any machine capable of executing instructions (sequentially or otherwise) that specify the actions to be performed by that machine. Furthermore, although only a single machine is shown, the term "machine" should also be understood to include any collection of machines that individually or collectively execute a set (or more sets) of instructions to perform any one or more methods discussed herein, such as cloud-based computing, Software as a Service (SaaS), other computer cluster configurations, etc.

[0090] As described herein, instances may include logic or multiple components, modules, or mechanisms, or operations performed through them. A module is a tangible entity (e.g., hardware) capable of performing a specified operation and can be configured or arranged in a certain way. In instances, circuitry may be arranged in a specified manner (e.g., internally or relative to an external entity such as other circuitry) as a module. In instances, all or part of one or more computer systems (e.g., stand-alone client or server computer systems) or one or more hardware processors may be configured by firmware or software (e.g., instructions, application portions, or applications) as modules that run to perform specified operations. In instances, software may reside on a machine-readable medium. In instances, when executed by the underlying hardware of the module, the software causes the hardware to perform the specified operations.

[0091] Accordingly, the term "module" should be understood to include tangible entities, meaning entities that are physically constructed, specially configured (e.g., hardwired), or temporarily (e.g., temporarily) configured (e.g., programmed) to operate in a specified manner or to perform part or all of the operations described herein. Consider instances where modules are temporarily configured, and each module does not need to be instantiated at any given time. For example, in the case where modules include general-purpose hardware processors configured using software, the general-purpose hardware processors can be configured as different modules at different times. The software can accordingly configure the hardware processors, for example, to constitute a specific module at one time instance and different modules at different time instances.

[0092] Machine (e.g., computer system) 500 may include a hardware processor 502 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a hardware processor core, or any combination thereof), main memory 504, and static memory 506, some or all of which may communicate with each other via interconnect (e.g., bus) 508. Machine 500 may also include a display unit 510, an alphanumeric input device 512 (e.g., a keyboard), and a user interface (UI) navigation device 514 (e.g., a mouse). In an example, display unit 510, input device 512, and UI navigation device 514 may be a touchscreen display. Machine 500 may also include a storage device (e.g., a drive) 516, a signal generating device 518 (e.g., a speaker), a network interface device 520, and one or more sensors 521, such as a global positioning system (GPS) sensor, a compass, an accelerometer, or other sensors. Machine 500 may include output controller 528, for example, serial (e.g., USB, parallel, or other wired or wireless (e.g., infrared (IR), near field communication (NFC), etc.) connections, for communicating or controlling one or more peripheral devices (e.g., printers, card readers, etc.).

[0093] Storage device 516 may include machine-readable medium 522 on which one or more sets of data structures or instructions 524 (e.g., software) are stored, which are embodied in or utilized by any one or more of the technologies or functions described herein. During execution thereon by machine 500, instructions 524 may also reside wholly or at least partially in main memory 504, static memory 506, or hardware processor 502. In this example, one or any combination of hardware processor 502, main memory 504, static memory 506, or storage device 516 may constitute a machine-readable medium.

[0094] Although machine-readable medium 522 is shown as a single medium, the term "machine-readable medium" can include a single medium or multiple media (e.g., a centralized or distributed database and / or associated caches and servers) configured to store one or more instructions 524.

[0095] The term "machine-readable medium" can include any medium capable of storing, encoding, or carrying instructions for execution by machine 500 and causing machine 500 to perform any one or more of the technologies disclosed herein, or capable of storing, encoding, or carrying data structures used by or associated with such instructions. Examples of non-limiting machine-readable media can include solid-state memory as well as optical and magnetic media. Therefore, machine-readable media are not transiently propagating signals. Specific examples of machine-readable media can include non-volatile memory, such as semiconductor storage devices (e.g., electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM)) and flash memory devices; disks, such as internal hard disks and removable disks; magneto-optical disks; random access memory (RAM); solid-state drives (SSDs); and CD-ROM and DVD-ROM disks.

[0096] Instruction 524 can be further sent or received via communication network 526, which is done via network interface device 520 using a transmission medium that utilizes any of a variety of transmission protocols, such as Frame Relay, Internet Protocol (IP), Transmission Control Protocol (TCP), User Datagram Protocol (UDP), Hypertext Transfer Protocol (HTTP), etc. Exemplary communication networks may include local area networks (LANs), wide area networks (WANs), packet data networks (e.g., the Internet), mobile phone networks (e.g., cellular networks), conventional telephone (POTS) networks, and wireless data networks (e.g., referred to as Wi-Fi). ® The Institute of Electrical and Electronics Engineers (IEEE) 802.11 family of standards, known as WiMAX ® The IEEE 802.16 family of standards), the IEEE 802.15.4 family of standards, and Bluetooth. ® Bluetooth ® Low power technology, ZigBee ® Point-to-point (P2P) networks, etc. In an example, network interface device 520 may include one or more physical jacks (e.g., Ethernet, coaxial, or telephone jacks) or one or more antennas to connect to communication network 526. In an example, network interface device 520 may include multiple antennas to perform wireless communication using at least one of single-input multiple-output (SIMO), multiple-input multiple-output (MIMO), or multiple-input single-output (MISO) technologies. The term "transmission medium" should be considered to include any intangible medium capable of storing, encoding, or carrying instructions executed by machine 500, and includes digital or analog communication signals or other intangible media to facilitate communication of such software.

[0097] This document uses conventional terminology from the fields of computer systems and computer networks. These terms are known in the art and are provided only as non-limiting examples for convenience. Therefore, unless otherwise stated, the interpretation of the corresponding terms in the claims is not limited to any particular definition.

[0098] Although specific embodiments have been illustrated and described herein, those skilled in the art will understand that any arrangement calculated to achieve the same purpose may be substituted for the specific embodiments shown. Many modifications will be apparent to those skilled in the art. Therefore, this application is intended to cover any adaptations or variations.

[0099] The above detailed description includes reference to the accompanying drawings, which are part of the detailed description. The drawings illustrate specific embodiments that can be practiced by way of illustration. These embodiments are also referred to herein as "examples". These examples may include elements other than those shown or described. However, the inventors also contemplate providing examples of only those elements shown or described. Furthermore, the inventors also contemplate examples of any combination or arrangement of those elements (or one or more aspects thereof) shown or described for a particular example (or one or more aspects thereof) or for other examples (or one or more aspects thereof) shown or described herein.

[0100] In this document, as is common in patent documents, the terms "a" or "an" are used to include one or more "a," independent of any other use of "at least one" or "one or more." In this document, unless otherwise stated, the term "or" is used to indicate non-exclusivity or that "A or B" includes "A but not B," "B but not A," and "A and B." Furthermore, in the appended claims, the terms "first," "second," and "third," etc., are used merely as labels and are not intended to impose numerical requirements on their objects. In this document, a sensor group may include one or more sensors, which may be of different types. Additionally, two different sensor groups may include one or more sensors belonging to both sensor groups.

[0101] In this detailed description, various features may have been grouped together to simplify this disclosure. This should not be construed as meaning that any unclaimed feature of the disclosure is essential to any claim. Rather, the subject matter of the invention may lie in fewer than all the features of a particular disclosed embodiment.

[0102] The above description is for illustrative purposes only and not for limitation. For example, the above examples (or one or more aspects thereof) may be used in combination with each other. Other embodiments may be used by those skilled in the art after reading the above description.

[0103] Various non-limiting embodiments have been described. It will be understood that suitable alternatives are possible without departing from the scope of the examples described herein. These and other examples are within the scope of the appended claims.

Claims

1. A system comprising: One or more data sources, comprising one or more sensors located at the food enterprise and connected to a network, wherein the one or more data sources are configured to: Track one or more events at the aforementioned food company; and Data is generated based on one or more events at the food company, the data relating to the food company's food safety risks and hygiene compliance tracking, wherein the data generated by the one or more sensors includes sensor data; and A server connected to a network, the server comprising: A data collection module configured to collect the data from the one or more data sources via the network; A database interaction module, configured to store data collected by the data collection module into a database and retrieve data from the database; and The predictive analytics module is configured to use predictive analytics algorithms to analyze data in the database to identify one or more trends and one or more predictive indicators, and to calculate the probability of future examinations leading to violations of health regulations based on the analyzed data.

2. The system of claim 1, wherein the one or more data sources further include at least one of the following: one or more distributors of the food enterprise, the one or more distributors being configured to generate distributor data; Pest control service, which generates pest control data; The health department conducts inspections, and these inspections generate health department inspection data. One or more users, who input self-audited data and / or self-reported data; And the service provider, which generates equipment maintenance and upkeep data.

3. The system of claim 1, wherein the one or more sensors of the food enterprise include at least one of the following: a thermometer, a hygrometer, and a barometer.

4. The system of claim 2, wherein the one or more dispensers comprise at least one of the following: a disinfectant dispenser and a water dispenser.

5. The system of claim 1, wherein when the calculated probability of a food company violating health regulations exceeds a threshold, the server sends a notification to one or more devices associated with the food company.

6. The system of claim 1, wherein the server further comprises: The report generation module is configured to generate reports that include the probability of food companies violating health regulations.

7. The system of claim 6, wherein the report generator is configured to send a report to a client device for display.

8. The system of claim 6, wherein the probability of the food enterprise violating health regulations includes a predicted risk score for the food enterprise.

9. The system of claim 8, wherein the probability of the food company violating health regulations includes a plurality of individual risk indicators for the food company, and wherein each of the plurality of individual risk indicators for the food company provides a risk assessment relative to other food companies.

10. The system of claim 9, wherein the multiple individual risk indicators of the food enterprise include personal hygiene, cleanliness and sanitation, time and temperature, and documentation.

11. A method implemented on at least one server connected to a network, the method comprising: One or more events at a food business are tracked using one or more data sources, said one or more data sources including one or more sensors located at the food business and connected to a network; Data is generated from one or more data sources based on one or more events at the food enterprise, and the data relates to the food enterprise's food safety risks and hygiene compliance tracking, wherein the data generated by the one or more sensors includes sensor data; The data is collected from the one or more data sources via the network; The collected data is stored in a database; Retrieve data from the database; Predictive analytics algorithms are used to analyze data in the database to identify one or more trends and one or more predictive indicators; and Based on the analyzed data, the probability of future examinations leading to violations of health regulations is calculated.

12. The method of claim 11, wherein the one or more data sources include at least one of the following: one or more distributors of the food enterprise, the one or more distributors being configured to generate distributor data; Pest control service, which generates pest control data; The health department conducts inspections, and these inspections generate health department inspection data. One or more users, who input self-audited data and / or self-reported data; And the service provider, which generates equipment maintenance and upkeep data.

13. The method of claim 11, wherein the one or more sensors of the food enterprise include at least one of the following: a thermometer, a hygrometer, and a barometer.

14. The method of claim 12, wherein the one or more dispensers comprise at least one of the following: a disinfectant dispenser and a water dispenser.

15. The method of claim 11, further comprising: When the calculated probability that a food company is violating health regulations exceeds a threshold, a notification will be sent to one or more devices associated with the food company.

16. A non-transitory computer-readable medium comprising instructions that, when executed by a computer, cause the computer to: One or more events at a food business are tracked using one or more data sources, said one or more data sources including one or more sensors located at the food business and connected to a network; Data is generated using the one or more data sources based on one or more events at the food company, the data being related to the food company's food safety risks and hygiene compliance tracking, wherein... The data generated by the one or more sensors includes sensor data; The data is collected from the one or more data sources via a network; The collected data is stored in a database; Retrieve data from the database; Predictive analytics algorithms are used to analyze data in the database to identify one or more trends and one or more predictive indicators. and Based on the analyzed data, the probability of future examinations leading to violations of health regulations is calculated.

17. The non-transitory computer-readable medium of claim 16, wherein the one or more data sources comprise at least one of: one or more dispensers of the food enterprise, the one or more dispensers being configured to generate dispenser data; Pest control service, which generates pest control data; The health department conducts inspections, and these inspections generate health department inspection data. One or more users, who input self-audited data and / or self-reported data; And the service provider, which generates equipment maintenance and upkeep data.

18. The non-transitory computer-readable medium of claim 16, wherein the one or more sensors of the food enterprise comprise at least one of the following: a thermometer, a hygrometer, and a barometer.

19. The non-transitory computer-readable medium of claim 17, wherein the one or more dispensers comprise at least one of: a disinfectant dispenser and a water dispenser.

20. The non-transitory computer-readable medium of claim 16, further comprising instructions that, when executed by a computer, cause the computer to: When the calculated probability that a food company is violating health regulations exceeds a threshold, a notification will be sent to one or more devices associated with the food company.

Images