Asset management method, system and device and storage medium

Abstract

The embodiment of the invention provides an asset management method, system and device and a storage medium, the method is executed by a data processing module, the method comprises the steps that measurement and control data of assets in a target area are acquired, the measurement and control data comprise monitoring images and / or monitoring data, and the assets comprise at least one of electric equipment, production and operation equipment and consumable; determining use state information of the assets based on the measurement and control data; determining an abnormal asset based on the use state information; and performing regulation and control management on the abnormal assets, wherein the regulation and control management comprises regulation and control of operation parameters and / or a circulation process.

Description

Technical Field

[0001] This specification relates to the field of asset management, and in particular to an asset management method, system, device and storage medium. Background Art

[0002] With the rapid development of the catering industry, the demand for asset management in catering stores is increasing, and asset management is directly related to operational efficiency, customer experience and cost control. Traditional asset management methods often rely on manual monitoring and operation, which has problems such as low efficiency and high loss rate.

[0003] Therefore, it is necessary to provide an asset management method, system, device and storage medium, with the help of technologies such as the Internet of Things, to achieve intelligent management of various types of assets, thereby effectively allocating assets and improving operational efficiency. Summary of the invention

[0004] One or more embodiments of the present specification provide an asset management method, which is executed by a data processing module, and includes: acquiring measurement and control data of assets in a target area, wherein the measurement and control data include surveillance images and / or monitoring data, and the assets include at least one of electrical equipment, production and operation equipment, and consumables; determining usage status information of the assets based on the measurement and control data; and determining abnormal assets based on the usage status information; and performing regulation and management on the abnormal assets, wherein the regulation and management includes regulating operating parameters and / or circulation processes.

[0005] One or more embodiments of the present specification provide an asset management system, the system comprising a monitoring module, an Internet of Things module, a data transmission module and a data processing module, the data transmission module comprising a network management platform; the monitoring module is configured to collect monitoring images of assets; the Internet of Things module is configured to collect identification data and sensor data; the data transmission module is configured to implement data interaction between the monitoring module, the Internet of Things module and the data processing module, and to implement data interaction between the data processing module and the network management platform; the network management platform is configured to obtain network interaction data; the data processing module is configured to: obtain measurement and control data of assets in a target area, the measurement and control data comprising the monitoring images and / or monitoring data, the assets comprising at least one of electrical equipment, production and operation equipment and consumables; determine the usage status information of the assets based on the measurement and control data; and determine abnormal assets based on the usage status information; and regulate and manage the abnormal assets, the regulation and management comprising regulating operating parameters and / or circulation processes.

[0006] One or more embodiments of the present specification provide an asset management device, which includes at least one storage medium and at least one processor, wherein the at least one storage medium is used to store computer instructions; and the at least one processor is used to execute the computer instructions to implement an asset management method.

[0007] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the asset management method described in the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 It is an application scenario diagram of the asset management method shown in some embodiments of this specification;

[0010] Figure 2 is a system structure diagram of an asset management system according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart of an asset management method according to some embodiments of this specification;

[0012] Figure 4 is an exemplary flow chart for determining the type of monitoring information according to some embodiments of this specification;

[0013] Figure 5 It is an exemplary schematic diagram of an association model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly introduces the drawings required for describing the embodiments. The drawings do not represent all implementation methods.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. If other words can achieve the same purpose, the words can be replaced by other expressions.

[0016] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] When the operations are performed according to the step description in the embodiments of this specification, unless otherwise specified, the order of the steps is interchangeable, the steps may be omitted, and other steps may be included in the operation process.

[0018] Figure 1 It is an application scenario diagram of the asset management method shown in some embodiments of this specification.

[0019] The application scenario may include assets 110, a monitoring module 120, an Internet of Things module 130, a network 140, and a processor 150, etc.

[0020] Assets 110 refer to resources related to production operations in the application scenario. Figure 1 As shown, asset 110 includes oven 111, air conditioner 112, etc.

[0021] The monitoring module 120 is configured to obtain monitoring images of the asset 110 .

[0022] The IoT module 130 is configured to acquire identification data and sensor data of the asset 110 .

[0023] The network 140 is configured to implement data interaction between the monitoring module 120 and the Internet of Things module 130 and the processor 150 and to obtain network interaction data. In some embodiments, the network 140 can be integrated into a data transmission module.

[0024] The processor 150 is configured to apply the asset management method in a variety of application scenarios. For example, the processor 150 determines the use status information of the asset based on the measurement and control data. For another example, the processor 150 determines an abnormal asset based on the use status information. For another example, the processor 150 regulates and manages the abnormal asset.

[0025] In some embodiments, processor 150 may be integrated as a data processing module.

[0026] In a typical application scenario, the monitoring module 120 and the Internet of Things module 130 obtain monitoring images, identification data and sensor data of the asset 110, and upload them to the network 140; the network 140 obtains network interaction data, and sends the monitoring images, identification data, sensor data and network interaction data to the processor 150; the processor 150 combines the monitoring images, identification data, sensor data and network interaction data into measurement and control data, and determines the usage status information of the asset based on the measurement and control data; the processor 150 determines abnormal assets based on the usage status information; the processor 150 regulates and manages abnormal assets through the network 140 and the Internet of Things module 130.

[0027] For detailed description of the above, please refer to Figures 2 to 5 Related description.

[0028] Figure 2 It is a system structure diagram of an asset management system according to some embodiments of this specification.

[0029] In some embodiments, Figure 2 As shown, the asset management system 200 includes a monitoring module 210 , an Internet of Things module 220 , a data transmission module 230 , and a data processing module 240 .

[0030] The monitoring module 210 is configured to collect monitoring images of the asset. In some embodiments, the monitoring module is configured on a monitoring device. The monitoring device includes at least one of a camera or a video camera.

[0031] The Internet of Things module 220 is configured to collect identification data and sensor data. In some embodiments, the Internet of Things module includes a server and an identification device and a sensor device. The server includes at least one of a local server or a cloud server.

[0032] The identification device is configured to identify the asset to obtain identification data. The sensing device is configured to detect the asset to obtain sensing data. The identification device includes a radio frequency identification (RFID) device, etc. The sensing device includes a gravity sensor, a temperature sensor, and a current sensor, etc. The current sensor includes a Hall current sensor, etc.

[0033] The IoT module is connected to the identification device and the sensor device in communication to collect the identification data and the sensor data.

[0034] The data transmission module 230 is configured to implement data interaction between the monitoring module, the Internet of Things module and the data processing module, and to implement data interaction between the data processing module and the network management platform.

[0035] In some embodiments, the data transmission module is configured as at least one of a communication network or a gateway, etc.

[0036] In some embodiments, the data transmission module 230 includes a network management platform 231. The network management platform 231 is configured to obtain network interaction data.

[0037] The gateway platform 231 is connected to the assets with communication functions to obtain network interaction data.

[0038] The data processing module 240 is configured to obtain measurement and control data of assets in the target area; determine usage status information of the assets based on the measurement and control data; determine abnormal assets based on the usage status information; and regulate and manage the abnormal assets.

[0039] In some embodiments, the data processing module 240 is further configured to collect monitoring images through monitoring devices deployed in at least one local area; obtain network interaction data through the network management platform; collect identification data and sensor data through the Internet of Things module; and generate monitoring data based on the network interaction data, identification data and sensor data. In some embodiments, the data processing module 240 is further configured to determine the type of monitoring information of the asset based on the measurement and control data; determine the key monitoring information of the asset based on the type of monitoring information; and determine the usage status information based on the key monitoring information.

[0040] In some embodiments, the data processing module 240 is further configured to generate at least one monitoring sequence group based on the measurement and control data; retrieve the monitoring image of the local area corresponding to the at least one monitoring sequence group; determine the associated image of the asset based on the monitoring image of the local area; and determine the monitoring information type of the asset based on the associated image and at least one monitoring sequence group.

[0041] In some embodiments, the data processing module 240 is further configured to determine a retention area of ​​the asset in at least one preset time period based on the monitoring data; determine abnormal usage characteristics of the asset based on the usage status information and the monitoring data; and determine the asset as an abnormal asset in response to at least one of the retention area and the abnormal usage characteristics failing to meet a preset condition.

[0042] In some embodiments, the data processing module includes a processor and a storage device, etc. The processor includes a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction processor (ASIP), a graphics processing unit (GPU), etc. or any combination thereof.

[0043] For detailed description of the above, please refer to Figures 3 to 5 Related description.

[0044] In some embodiments of the present specification, based on the asset management system and its modules, the informatization and intelligence of asset management can be realized, thereby effectively allocating assets and improving operational efficiency.

[0045] It should be noted that the above description of the asset management system is only for convenience of description and does not limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem connected with other modules without deviating from this principle.

[0046] Figure 3 is an exemplary flow chart of an asset management method according to some embodiments of this specification. Figure 3 As shown, the process 300 includes the following steps. In some embodiments, the process 300 can be executed by a data processing module.

[0047] In some embodiments, the data processing module obtains measurement and control data of assets in the target area; determines usage status information of the assets based on the measurement and control data; determines abnormal assets based on the usage status information; and regulates and manages the abnormal assets.

[0048] Step 310, obtaining measurement and control data of assets in the target area.

[0049] The target area refers to an area that needs to be managed. In some embodiments, the target area includes at least one of a restaurant, a bakery, etc.

[0050] In some embodiments, the data processing module divides the target area into at least one local area by any feasible method such as grid division. The number and range of the local areas are pre-set by the user based on the production and operation conditions of the target area. For example, the user sets the back kitchen, cashier counter and dining area in a restaurant as a local area respectively. The user refers to the staff of the target area.

[0051] The local area refers to a part of the target area. In some embodiments, the data processing module represents the local area by numbers or letters.

[0052] Assets refer to resources required for production and operation in the target area. In some embodiments, assets include at least one of electrical equipment, production and operation equipment, and consumables.

[0053] Electrical equipment refers to equipment that needs to use electrical energy, for example, at least one of electric lights, air conditioners, and stereos.

[0054] Production and operation equipment refers to equipment related to production and operation, for example, at least one of a beverage machine, oven, stove, etc. Among them, a production and operation equipment may also be an electrical equipment.

[0055] Consumables refer to items that may be consumed during production and operation, such as at least one of plates, bowls, etc.

[0056] In some embodiments, the data processing module numbers each asset and represents the asset with the asset number.

[0057] Measurement and control data refers to data obtained by monitoring and / or supervising an asset. In some embodiments, the measurement and control data includes monitoring images and / or monitoring data.

[0058] Surveillance images refer to image data obtained by monitoring assets.

[0059] In some embodiments, the data processing module obtains the monitoring image through the data transmission module. The monitoring device deployed in at least one local area uploads the collected monitoring image to the data transmission module.

[0060] In some embodiments, the data processing module organizes the surveillance images of multiple local areas into multiple groups of data, each group of data corresponding to a surveillance image of a local area, wherein a surveillance image of a local area includes surveillance images in multiple time periods and the acquisition time of each surveillance image.

[0061] In some embodiments, the data processing module can pre-set a time period. For example, the data processing module uses every 1 hour or every 2 hours as a time period. The time period can also be pre-set by the user based on historical experience. For example, the user divides 24 hours into 24 sampling points, and uses the time between any two adjacent sampling points as a time period. For another example, reduce the number of sampling points at midnight.

[0062] Monitoring data refers to data obtained by monitoring an asset. In some embodiments, the monitoring data includes network interaction data, identification data, and sensor data.

[0063] The network interaction data refers to data uploaded by the asset related to the operating status. In some embodiments, the network interaction data includes at least one of working parameters and working status.

[0064] Working parameters refer to parameters related to the operation of an asset. In some embodiments, working parameters include the current operating power, preset power, and preset temperature of the asset.

[0065] The working status is used to reflect whether the asset is running. The working status includes at least one of open and closed.

[0066] In some embodiments, the data processing module obtains network interaction data of each asset through the network management platform. The asset uploads the network interaction data to the network management platform.

[0067] In some embodiments, the data processing module organizes the network interaction data uploaded by multiple assets into multiple data entries, each of which includes the asset number, the number of the local area where the asset is located, the network interaction data uploaded by the asset, and the time when the network interaction data was uploaded, etc. The asset number and the number of the local area where the asset is located are stored in the storage device.

[0068] Identification data refers to data obtained by identifying an asset. Identification data includes asset number, RFID number, asset usage status, and the number of the local area where the asset is located. Among them, the usage status includes at least one of being in use or standby. Identification time refers to the time when the identification data is collected.

[0069] In some embodiments, an RFID tag is provided on the asset, and the identification device collects identification data by reading the RFID tag on the asset. The identification device uploads the identification data to the Internet of Things module, which then uploads the identification data to the data processing module via the data transmission module.

[0070] In some embodiments, the data processing module organizes the identification data collected by the identification device into multiple identification entries, each identification entry including the asset number, RFID number, asset usage status, number of the local area where the asset is located, and identification time.

[0071] The sensor data refers to data obtained by detecting an asset. In some embodiments, the sensor data includes at least one of gravity data, temperature data, and current data.

[0072] Gravity data refers to the gravity carried by the asset. Temperature data refers to the temperature of the asset. Current data refers to the magnitude of the current passing through the asset. Sensor data is collected through sensors such as gravity sensors, temperature sensors, and current sensors in the sensor equipment.

[0073] For example, a gravity sensor is configured at the bottom of a dinner plate to collect the gravity of the dinner plate. A temperature sensor is configured on the surface of a dining table to collect the temperature of the surface of the dining table. A current sensor is configured in an electrical device to collect the magnitude of the current passing through the electrical device.

[0074] In some embodiments, the sensor device uploads the sensor data to the Internet of Things module. The Internet of Things module uploads the sensor data to the data processing module through the data transmission module.

[0075] In some embodiments, the data processing module organizes the sensor data collected by the sensor device into multiple sensor entries, each identification entry includes an asset number, sensor data corresponding to the asset, the number of the local area corresponding to the sensor data, and the collection time, etc. The collection time refers to the time when the sensor data is collected.

[0076] In some embodiments, the data processing module generates monitoring data based on the network interaction data, the identification data and the sensor data.

[0077] For more information about monitoring devices, identification devices, sensor devices, and asset management system modules, see Figure 2 and its related description.

[0078] Step 320, determining the usage status information of the asset based on the measurement and control data.

[0079] The usage status information refers to data related to the usage of the asset. In some embodiments, the usage status information includes at least one of an operating status, an apparent status, and a position status.

[0080] The operating status is used to reflect whether the asset is operating normally. The operating status includes normal operation, abnormal operation and uncertain status. Among them, uncertain status means that the operating status cannot be accurately determined.

[0081] The apparent state is used to reflect the appearance of the asset. The apparent state includes normal appearance, abnormal appearance and uncertain appearance. Among them, abnormal appearance refers to the situation where the appearance of the asset is damaged. Uncertain appearance means that the apparent state cannot be accurately determined.

[0082] The location status is used to reflect the relationship between the preset location and the current location of the asset. The location status includes normal location, abnormal location, or uncertain location. Normal location means that the preset location and the current location of the asset are consistent. Abnormal location means that the preset location and the current location of the asset are inconsistent. Uncertain location means that the location status cannot be accurately determined. The current location refers to the local area where the asset is currently located. The preset location refers to the local area where the asset is located in a normal working state. Among them, the preset location is pre-set by the user based on usage needs.

[0083] In some embodiments, the usage status information of different types of assets includes different amounts and types of data. For example, the usage status information of tableware includes the apparent state and the position state, and the usage status information of fixed-position electrical equipment includes the operating state and the apparent state.

[0084] In some embodiments, the data processing module determines the usage status information of the asset in a variety of ways based on the measurement and control data. For example, the data processing module takes the asset whose usage status information needs to be determined as the target asset, constructs a vector to be matched based on the network interaction data, identification data, and sensor data corresponding to the target asset in the monitoring data, matches the reference vector that meets the matching conditions in the reference vector database, and determines the usage status information of the asset based on the label of the reference vector. Among them, the vector to be matched refers to a feature vector constructed by network interaction data, identification data, and sensor data. The matching condition includes that the vector distance to the vector to be matched is less than the distance threshold. The vector distance includes the Euclidean distance, etc.

[0085] The reference vector library is built based on historical data, including multiple reference vectors and labels corresponding to each reference vector. A reference vector refers to a feature vector built from historical network interaction data, historical identification data, and historical sensor data. The label corresponding to a reference vector is the historical usage status information of the historical asset corresponding to the reference vector.

[0086] In some embodiments, the data processing module counts the labels of multiple reference vectors that meet the matching conditions, and determines the usage status information of the target asset based on the statistical results.

[0087] Taking the operating status as an example, the data processing module counts the number of labels with normal operating status in the labels of multiple reference vectors, and calculates the ratio of the number of labels with normal operating status to the total number of labels to obtain the normal ratio. If the normal ratio is not less than the first threshold, the operating status of the target asset is normal; if the normal ratio is not greater than the second threshold, the operating status of the target asset is abnormal; if the normal ratio is greater than the second threshold and less than the first threshold, the operating status of the target asset is uncertain.

[0088] The first threshold and the second threshold are preset based on historical experience, and the first threshold is greater than the second threshold. The method for determining the apparent state and the position state is similar to the method for determining the operating state described above.

[0089] In some embodiments, the data processing module further obtains image features based on the monitoring images by any feasible method such as image feature extraction, and determines the asset usage status information based on the image features. The image features refer to features related to the assets in the monitoring images.

[0090] Exemplarily, the data processing module determines whether the operating status is normal or abnormal based on whether the asset in the image feature can be turned on normally; determines whether the apparent status is normal or abnormal based on whether the asset in the image feature is damaged; and determines whether the position status is normal or abnormal based on whether the asset in the image feature is in a preset position.

[0091] The data processing module determines the usage status information of each asset through any of the above methods.

[0092] In some embodiments, if any data in the asset usage status information is uncertain, the data processing module can send a notification warning to the terminal device used by the user. The notification warning may be in any feasible form such as text notification or voice notification. The terminal device may include a smart phone or a tablet computer.

[0093] In some embodiments, the IoT module further includes a mutual inductance coil component and an intelligent circuit breaker component. The mutual inductance coil component is configured to monitor the power consumption of the asset. The intelligent circuit breaker component is configured to monitor and / or control the circuit state of the asset. The circuit state includes circuit connection or circuit disconnection.

[0094] In some embodiments, the Internet of Things module uploads the data collected by the mutual inductance coil component and the intelligent circuit breaker component to the data processing module. The data processing module determines the working state of the asset based on the uploaded power consumption and circuit state. For example, if the power consumption is not 0 and the circuit state is circuit connected, the working state of the asset is turned on.

[0095] In some embodiments of the present specification, the power consumption and circuit status of an asset can be automatically monitored through a mutual inductance coil component and an intelligent circuit breaker component, thereby quickly determining the operating status of the asset.

[0096] In some embodiments, the data processing module determines the type of monitoring information of the asset based on the measurement and control data; determines the key monitoring information of the asset based on the monitoring information type; and determines the usage status information based on the key monitoring information.

[0097] The monitoring information type refers to the type of measurement and control data used to identify whether an asset is an abnormal asset. In some embodiments, the monitoring information type includes at least one of power consumption, temperature data, location status, and apparent status. For an explanation of abnormal assets, see step 330 and its related description.

[0098] In some embodiments, the types of monitoring information of the same type of assets in different local areas may be the same or different. The types of monitoring information of the same type of assets in different time periods may be the same or different.

[0099] In some embodiments, the data processing module determines the monitoring information type of the asset based on the measurement and control data by a variety of methods. For example, the data processing module takes the asset for which the monitoring information type needs to be determined as the target asset, queries the reference time period and reference local area in the store table that are the same as the time period and local area based on the time period for obtaining the measurement and control data corresponding to the target asset and the local area where the target asset is located, and determines the reference information type corresponding to the reference time period and reference local area as the monitoring information type of the target asset.

[0100] The store table is pre-set based on historical data, including multiple reference information and reference information types corresponding to each reference information. The reference information includes a reference time period and a reference local area. The reference information type refers to the monitoring information type of the historical asset corresponding to the reference information.

[0101] In some embodiments, the data processing module counts historical abnormal assets in historical data, obtains the historical time period of historical measurement and control data corresponding to the historical abnormal assets, and the historical local area where the historical assets are located as reference information, and uses the type of historical abnormal data of the historical abnormal assets as the reference information type corresponding to the reference information. Among them, abnormal data refers to the measurement and control data that determines that the asset is an abnormal asset. The historical abnormal data is determined by the user through manual inspection of the historical abnormal assets.

[0102] In some embodiments, the data processing module determines the type of monitoring information of the asset based on the measurement and control data and the flow of people. For example, the data processing module dynamically adjusts the time period based on the flow of people, and determines the type of monitoring information of the asset in different time periods based on the measurement and control data corresponding to the adjusted time period.

[0103] The flow of people refers to the number of people entering the target area. The data processing module determines the monitoring information type of the asset in different time periods based on the measurement and control data corresponding to the adjusted time period and through the above method for determining the monitoring information type based on the measurement and control data.

[0104] In some embodiments, the Internet of Things module includes an access control device or an infrared sensing device, etc., and is set at the entrance of the target area. The access control device or the infrared sensing device is configured to collect the flow of people at multiple sampling points and send the flow of people at multiple sampling points to the data processing module. For an explanation of the sampling points, see step 310 and its related description.

[0105] In some embodiments, the data processing module counts the flow of people at multiple sampling points and the rate of change of the flow of people at each sampling point relative to the flow of people at a basic sampling point, calculates the number of multiple sampling points whose change rate increases continuously to obtain a first number, and takes the time span between these sampling points and the first number of sampling points subsequent to these sampling points as a time period.

[0106] The basic sampling point refers to the sampling point where the flow of people is not less than the preset flow of people for the first time. The preset flow of people is pre-set based on historical experience. The rate of change of the flow of people at the sampling point relative to the flow of people at the basic sampling point refers to the ratio of the flow of people at the sampling point to the flow of people at the basic sampling point.

[0107] Exemplarily, there are 5 sampling points, and the change rate of the pedestrian flow at these 5 sampling points relative to the pedestrian flow at the basic sampling point is (5%, 7%, 10%, 0, -5%), then the time span between the sampling points where the change rate continuously increases (the first 3 sampling points) and the 3 sampling points subsequent to the first 3 sampling points is taken as a time period.

[0108] In some embodiments of the present specification, since assets are more likely to become abnormal when there is a large flow of people, dynamically adjusting the time period based on the flow of people can more accurately determine the type of monitoring information of assets when there is a large flow of people, thereby promptly discovering abnormal assets.

[0109] In some embodiments, the data processing module generates at least one monitoring sequence group based on the measurement and control data; retrieves the monitoring image of the local area corresponding to the at least one monitoring sequence group; determines the associated image of the asset based on the monitoring image of the local area; and determines the monitoring information type of the asset based on the associated image and the at least one monitoring sequence group. Figure 4 And related instructions.

[0110] Key monitoring information refers to the measurement and control data corresponding to the monitoring information type.

[0111] In some embodiments, the data processing module determines the key monitoring information of the asset based on the monitoring information type. For example, the data processing module selects the key monitoring information corresponding to the monitoring information type from the measurement and control data and / or historical measurement and control data based on the monitoring information type.

[0112] In some embodiments, the data processing module determines the usage status information of the asset based on the key monitoring information through the above-mentioned method of determining the usage status information based on the measurement and control data.

[0113] In some embodiments of the present specification, by determining the type of monitoring information, it is possible to obtain measurement and control data that is more useful for determining whether an asset is an abnormal asset, thereby reducing the amount of data processing and improving data processing efficiency.

[0114] In some embodiments, the data processing module determines the usage status information based on the key monitoring information through the status layer of the association model. Figure 5 And related instructions.

[0115] Step 330, determining abnormal assets based on the usage status information.

[0116] Abnormal assets refer to assets with abnormal usage status information.

[0117] In some embodiments, the data processing module determines the abnormal asset in a variety of ways. For example, in response to the asset's usage status information meeting a preset abnormal condition, the data processing module determines the asset as an abnormal asset. The preset abnormal condition includes at least one of the operating state, apparent state, and position state in the usage status information being abnormal.

[0118] In some embodiments, the data processing module determines the retention area of ​​the asset in at least one preset time period based on the monitoring data; determines the abnormal usage characteristics of the asset based on the usage status information and the monitoring data; and determines the asset as an abnormal asset in response to at least one of the retention area and the abnormal usage characteristics not satisfying a preset condition.

[0119] The retention area refers to the local area where the asset is located during a preset period of time. The preset period is pre-set based on historical experience and includes one or more time periods.

[0120] In some embodiments, the data processing module queries and identifies at least one local area in the data where the asset is located within the preset time period based on the monitoring data and the preset time period, and determines the at least one local area as the retention area of ​​the asset within the preset time period.

[0121] Abnormal usage characteristics refer to data related to abnormal operation of assets. For example, abnormal usage characteristics are asset operating parameters or temperature data.

[0122] In some embodiments, the data processing module determines the abnormal usage characteristics of the asset in a variety of ways. For example, the data processing module uses the abnormal usage status information and monitoring data as the abnormal usage characteristics of the asset based on the usage status information and monitoring data.

[0123] For example, if the operating state of the asset is abnormal operation, the data processing module uses the operating parameters of the asset as abnormal use characteristics. If the temperature data of the asset in the identification data exceeds the preset temperature, the data processing module uses the temperature data of the asset as abnormal use characteristics. The preset temperature is pre-set based on historical experience.

[0124] In some embodiments, the data processing module determines abnormal usage characteristics based on the monitoring sequence group. For more information about the monitoring sequence group, see Figure 4 Related instructions.

[0125] In some embodiments, the data processing module determines the abnormal use characteristics of the asset based on the monitoring data of multiple continuous time periods in the monitoring sequence group. For example, for any data in the monitoring sequence group, in response to the data continuously changing in the same direction in multiple continuous time periods, the data processing module determines the data as an abnormal use characteristic. The continuous change in the same direction refers to a continuous increase or a continuous decrease.

[0126] Exemplarily, with respect to the temperature data of the refrigerator, in response to a continuous decrease in the temperature data in a plurality of consecutive time periods, the data processing module determines the temperature data as an abnormal usage feature corresponding to the refrigerator.

[0127] In some embodiments of the present specification, by analyzing changes in monitoring data of an asset over multiple consecutive time periods, abnormal usage characteristics of the asset can be more accurately determined, providing effective data support for subsequent determination of abnormal assets.

[0128] In some embodiments, the data processing module determines abnormal assets in a variety of ways. For example, in response to at least one of the retention area and the abnormal use characteristics not meeting a preset condition, the data processing module determines the asset as an abnormal asset. The preset condition includes that the retention area does not match the preset area or there is at least one abnormal use characteristic. The preset area refers to the local area where the asset should be located during a preset period of time.

[0129] In some embodiments, the data processing module determines the preset area of ​​the asset by querying the retention table based on the preset time period. The retention table is preset based on historical experience, including preset areas corresponding to different assets in different preset time periods. In some embodiments, the data processing module selects historical assets with normal usage status information from a large amount of historical data, and takes multiple historical retention areas of such historical assets in a single historical preset time period as preset areas, and counts them into the retention table.

[0130] In some embodiments, the data processing module obtains user behavior characteristics in the target area based on the Internet of Things module; based on the user behavior characteristics, updates the preset retention time of the asset; in response to the actual retention time of the asset being not less than the preset retention time, determines the asset as an abnormal asset and issues a warning.

[0131] User behavior characteristics refer to characteristics related to the user's behavior in the target area, and include at least one of the number of people who check out, the number of people who leave the store, and the number of people who leave their seats.

[0132] In some embodiments, the IoT module counts the checkout records of customers through the store's backend system to obtain the number of checkouts; obtains the number of people leaving the store through an access control device or an infrared sensor; obtains gravity data through a gravity sensor set under the seat, and determines the number of people leaving the seat based on the gravity data. For example, if the value of the gravity data changes to 0 and continues for the preset departure time, the number of people leaving the seat increases by 1. The preset departure time refers to the time used to determine that the customer has left the seat. The preset departure time is preset based on historical experience.

[0133] The preset retention time refers to the time that the asset should remain in the retention area.

[0134] In some embodiments, the data processing module updates the preset retention time of the asset based on the user behavior characteristics. For example, the data processing module calculates the average of the number of people who check out and the number of people who leave the store, and calculates the difference between the average and the number of people who leave the store and adds 1 to obtain an updated value, and multiplies the updated value by the original preset retention time as the updated preset stay time. The data processing module can also directly calculate the difference between the number of people who leave the store and the number of people who leave the store and add 1 to obtain an updated value.

[0135] In some embodiments, the original preset stay time refers to the preset stay time of the asset in the previous preset period of time before the current preset period of time. For a type of asset, the data processing module calculates the average stay time of the asset in the retention area in the previous preset period of time, and uses the average stay time as the original preset stay time of the asset.

[0136] Actual retention time refers to the time that the assets actually remain in the retention area.

[0137] In some embodiments, the data processing module determines the actual retention time of the asset based on the measurement and control data. For example, the data processing module counts the identification time of the asset in the retention area in the identification data, and uses the time span of the identification time as the actual retention time of the asset.

[0138] In some embodiments, in response to the actual retention time of the asset being not less than the preset retention time, the data processing module determines the asset as an abnormal asset and issues a notification warning to the user. For an explanation of the notification warning, refer to step 320 and its related description.

[0139] In some embodiments of the present specification, user behavior and traffic flow in the target area will affect the residence time of the asset in the retention area to a certain extent. By identifying user behavior characteristics, the preset retention time of the asset can be updated in a timely manner, and then the actual retention time can be used to dynamically determine whether the asset is an abnormal asset.

[0140] In some embodiments of the present specification, whether an asset is an abnormal asset can be identified in a timely manner by determining whether the asset is in a retention area and whether the asset has abnormal usage characteristics, thereby ensuring the timeliness and effectiveness of asset management.

[0141] Step 340: Regulate and manage abnormal assets.

[0142] In some embodiments, regulating management includes regulating operating parameters and / or flow processes. Regulating operating parameters includes changing the operating power of the asset. Regulating the flow process includes changing the location of the asset.

[0143] In some embodiments, the data processing module regulates and manages the abnormal assets based on the usage status information of the abnormal assets, and then adjusts the abnormal assets to assets with normal usage status information. For example, if the temperature data of the refrigerator is higher than the set temperature of the refrigerator, the data processing module increases the operating power of the refrigerator so that the temperature data of the refrigerator is the same as the set temperature of the refrigerator. For example, if the position status of the tableware is abnormal, the data processing module sends a notification warning to the terminal device used by the user, and the user moves the tableware to the preset position after receiving the notification warning. Among them, the refrigerator set temperature refers to the temperature of the refrigerator in normal working condition. The refrigerator set temperature is pre-set by the user based on usage needs. For instructions on the preset position, see step 320 and related descriptions.

[0144] In some embodiments of the present specification, by acquiring real-time measurement and control data of assets, more reliable usage status information can be determined, thereby accurately judging whether an asset is an abnormal asset, and timely regulating and managing abnormal assets to ensure normal use of assets and improve operational efficiency.

[0145] Figure 4 is an exemplary flow chart for determining the type of monitoring information according to some embodiments of this specification. Figure 4 As shown, the process 400 includes the following steps. In some embodiments, the process 400 can be executed by a data processing module.

[0146] In some embodiments, the data processing module generates at least one monitoring sequence group based on the measurement and control data; retrieves the monitoring image of the local area corresponding to the at least one monitoring sequence group; determines the associated image of the asset based on the monitoring image of the local area; and determines the monitoring information type of the asset based on the associated image and at least one monitoring sequence group.

[0147] Step 410: Generate at least one monitoring sequence group based on the measurement and control data.

[0148] A monitoring sequence group refers to a collection of measurement and control data related to a single asset. In some embodiments, a single monitoring sequence group includes measurement and control data of a single asset in multiple time periods.

[0149] In some embodiments, the data processing module generates at least one monitoring sequence group based on the measurement and control data. For example, the data processing module uses the asset for which the monitoring sequence group needs to be generated as the target asset, counts multiple identification entries corresponding to the target asset in the identification data, extracts the identification time from the multiple identification entries, uses the time period containing the identification time as the target time period, and divides the measurement and control data corresponding to the target asset in the target time period into a monitoring sequence group. For a description of the identification entries, see Figure 3 and its related description.

[0150] Step 420: retrieve a monitoring image of a local area corresponding to at least one monitoring sequence group.

[0151] In some embodiments, the data processing module retrieves monitoring images of a local area corresponding to at least one monitoring sequence group based on at least one monitoring sequence group, wherein the local area corresponding to the monitoring sequence group refers to at least one local area where the asset corresponding to the monitoring sequence group is located within the target time period.

[0152] Step 430, determining the associated image of the asset based on the surveillance image of the local area.

[0153] An asset's associated images refer to surveillance images related to the asset.

[0154] In some embodiments, the data processing module determines the surveillance image containing the target asset as the associated image of the target asset by any feasible method such as an image recognition algorithm based on the surveillance image of the local area corresponding to the target asset.

[0155] Step 440 , determining the type of monitoring information of the asset based on the associated image and at least one monitoring sequence group.

[0156] In some embodiments, the data processing module counts the acquisition time of each surveillance image in the associated images, determines the time span of the acquisition time as the time period to be matched, and determines the monitoring information type of the target asset by querying the store table in step 320 based on the local area corresponding to the time period to be matched and the monitoring sequence group.

[0157] The data processing module determines the monitoring information type of each asset through the above method.

[0158] In some embodiments, the data processing module determines missing data of the asset based on at least one monitoring sequence group, and determines the type of monitoring information of the asset based on the missing data.

[0159] Missing data refers to the data that is missing in the monitoring sequence group corresponding to the asset.

[0160] In some embodiments, the data processing module traverses the data of the monitoring sequence group, and if it is found that the data in the monitoring sequence group is discontinuous in time, the data is confirmed to be missing. For example, in the identification data of the monitoring sequence group corresponding to the asset, if the identification time of two adjacent identification items exceeds the missing time threshold, it is determined that the identification data is missing some identification items, and the identification data is missing data. The missing time threshold is preset based on historical experience.

[0161] In some embodiments, the data processing module queries the missing comparison table for the monitoring information type corresponding to the missing data based on the missing data, and uses the obtained monitoring information type as the monitoring information type of the asset.

[0162] The missing comparison table is pre-set based on historical data, including multiple assets, multiple missing data for each asset, and the monitoring information type corresponding to each missing data. In some embodiments, the data processing module counts historical assets with historical missing data in the historical data, screens historical abnormal assets among such historical assets, and uses the monitoring information type corresponding to the historical abnormal assets as the monitoring information type of the asset under the corresponding missing data and includes it in the missing comparison table.

[0163] In some embodiments, the data processing module determines the type of monitoring information based on the associated image and monitoring data through the monitoring layer of the associated model. Figure 5 Related instructions.

[0164] In some embodiments of the present specification, abnormal assets can be accurately identified by determining the associated images corresponding to the assets and combining them with the monitoring sequence group to determine a more reasonable type of monitoring information for the assets.

[0165] It should be noted that the above description of the process 200 and the process 300 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0166] Figure 5 It is an exemplary schematic diagram of an association model according to some embodiments of the present specification.

[0167] In some embodiments, the correlation model 520 includes a monitoring layer 521 and a status layer 522 .

[0168] The monitoring layer is used to determine the type of monitoring information of the asset. In some embodiments, the monitoring layer is a machine learning model, for example, any one or combination of a convolutional neural network (CNN) model or other custom model structures.

[0169] The input of the monitoring layer includes associated images 511, monitoring data 512 corresponding to the associated images, and standard images 513. The output of the monitoring layer is the monitoring information type 530 of the asset. Among them, the monitoring data corresponding to the associated image refers to the monitoring data of the asset within the time span composed of the acquisition moments of the associated images. For a description of monitoring data, monitoring information type, standard images, and associated images, see Figure 3 and Figure 4 and its related description.

[0170] The standard image refers to the monitoring image of the asset in normal working condition. The data processing module uses the monitoring image of the asset in normal working condition in the historical data as the standard image and stores it in the storage device.

[0171] In some embodiments, the data processing module trains the monitoring layer based on a large number of first training samples with first labels by gradient descent method or the like. The first training samples include sample associated images corresponding to the sample assets, sample standard images, and sample monitoring data corresponding to the sample associated images. The first label is the actual monitoring information type of the sample asset.

[0172] In some embodiments, the first training sample and the first label are determined based on historical data. In some embodiments, the data processing module uses historical assets in historical data as sample assets, historical associated images, historical standard images, and historical monitoring data corresponding to historical associated images corresponding to historical assets as first training samples, and uses historical investigation results of historical assets as first labels. The investigation results refer to the results of manual investigations, including the actual monitoring information types of historical assets. Manual investigations refer to investigations by users on the types of monitoring information that may correspond to abnormalities in assets.

[0173] In some embodiments, the monitoring layer can be trained in the following manner: inputting the first training sample into the initial monitoring layer, constructing a loss function based on the output of the initial monitoring layer and the first label, iteratively updating the initial monitoring layer based on the loss function, and completing the monitoring layer training when the loss function of the initial monitoring layer meets the preset training condition. The preset training condition may be that the loss function converges, the number of iterations reaches a set value, etc.

[0174] The state layer is used to determine the probability distribution of the asset's usage state information. In some embodiments, the state layer is a machine learning model, such as any one or combination of a neural network (NN) model or other custom model structures.

[0175] The input of the status layer includes the key monitoring information 540 of the asset and / or the time period for collecting the key monitoring information 540, and the output of the status layer is the probability distribution 550 of the asset's usage status information. The probability distribution of the asset's usage status information includes at least one of the probability value of the operating state, the probability value of the apparent state, and the probability value of the position state. The probability value is a numerical value between 0 and 1. The larger the probability value, the greater the probability that the usage status information is in a normal state, and the smaller the probability value, the greater the probability that the usage status information is in an abnormal state. The time period for collecting key monitoring information is determined by the measurement and control data. For a description of the measurement and control data and usage status information, see Figure 3 and its related description.

[0176] In some embodiments, the data processing module determines the usage status information based on the probability distribution of the usage status information of the asset by judging the relationship between the probability value and the first probability threshold and the second probability threshold. For example, in the probability distribution of the usage status information of the asset, if the probability value of the operating status is not less than the first probability threshold, the operating status is normal operation; if the probability value of the operating status is not greater than the second probability threshold, the operating status is abnormal operation; if the probability value of the operating status is greater than the second probability threshold and less than the first probability threshold, the operating status is uncertain. The method for determining the apparent state and the position state is similar to the above-mentioned method for determining the operating state.

[0177] In some embodiments, the first probability threshold and the second probability threshold are preset by the user or determined based on historical data. For example, the user actually verifies each output result of the state layer in the historical data, obtains the actual probability value of each output result, screens multiple output results whose actual probability values ​​are within a preset probability range, takes the maximum value of the multiple output results as the first probability threshold, and takes the minimum value of the multiple output results as the second probability threshold. The preset probability range is preset based on historical experience. For example, 45%-55%.

[0178] The actual probability value of the output result is used to characterize the reliability of the output result. Since multiple output results of the status layer may be repeated, the actual probability value of an output result can be determined by the same multiple output results. For example, if the status layer outputs 0.45 ten times in the historical time, the actual probability value of 0.45 is jointly determined by the actual asset verification results corresponding to the 10 0.45s. The actual asset verification results include whether the operating status of the asset is normal or abnormal.

[0179] Exemplarily, there are 10 output results with a probability value of 0.45 for the operating status. After actual verification of the assets corresponding to these 10 output results, it is found that among the assets corresponding to these 10 output results, 5 assets have a normal operating status and 5 assets have an abnormal operating status. Then, the actual probability value of the output result with a probability value of 0.45 for the operating status is 50%.

[0180] In some embodiments, the first probability threshold and the second probability threshold corresponding to the operating state, the apparent state and the position state are different and are determined respectively by the above method.

[0181] In some embodiments, the data processing module trains the state layer based on a large number of second training samples with second labels by a gradient descent method or other methods. The second training samples include sample key monitoring information and / or a sample time period for collecting sample key monitoring information, and the second training samples are obtained based on historical data.

[0182] The second label is the actual probability distribution of the historical usage status information of the historical asset corresponding to the second training sample. The second label is obtained based on historical data. In some embodiments, the data processing module counts the actual operation of the historical asset corresponding to the second training sample in the sample time period in the historical data. For example, in the historical data, there are 10 operating states determined by the historical asset in the sample time period, of which 8 times the operating state is abnormal. The probability of abnormal operation of the historical asset in the sample time period is 80% (exceeding the preset abnormal threshold), and the probability value of the operating state in the second label is 0, indicating that the operating state is abnormal.

[0183] The actual operation status is determined by the user's actual verification of the asset. The preset abnormality threshold refers to the probability of determining an abnormality in a historical asset within a sample time period. The preset abnormality threshold is pre-set based on historical experience. For example, 75%.

[0184] In some embodiments, the training process of the state layer is similar to the training process of the monitoring layer, and its training process can refer to the training process of the monitoring layer.

[0185] In some embodiments of the present specification, the key monitoring information of the asset is determined through the monitoring layer, the probability distribution of the asset's usage status information is determined through the status layer, and then the asset's usage status information is determined, and the result obtained is more accurate.

[0186] Some embodiments of this specification provide an asset management device, including at least one processor and at least one memory. The at least one memory is used to store computer instructions, and the at least one processor is used to execute at least part of the computer instructions to implement the asset management method described in the above embodiment.

[0187] Some embodiments of this specification provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the asset management method described in the above embodiments.

[0188] Furthermore, certain features, structures or characteristics in one or more embodiments of this specification may be appropriately combined.

[0189] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0190] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the materials cited in this specification and the contents described in this specification, the descriptions, definitions, and / or usage of terms in this specification shall prevail.

Claims

1. An asset management method, characterized in that: The method is performed by a data processing module and includes: Acquire measurement and control data of assets in the target area, the measurement and control data including surveillance images and / or monitoring data, and the assets including at least one of electrical equipment, production and operation equipment, and consumables; Determining usage status information of the asset based on the measurement and control data; Based on the usage status information, determining abnormal assets; and The abnormal assets are regulated and managed, and the regulation and management includes regulating operating parameters and / or circulation processes.

2. The method according to claim 1, characterized in that The monitoring data includes network interaction data, identification data and / or sensor data; The obtaining of measurement and control data of assets in the target area includes: Collecting the monitoring image by a monitoring device deployed in at least one local area; Obtaining the network interaction data through a network management platform; Collecting the identification data and the sensor data through an Internet of Things module; and generating the monitoring data based on the network interaction data, the identification data and the sensor data; The determining, based on the measurement and control data, the usage status information of the asset comprises: Determining the type of monitoring information of the asset based on the measurement and control data; Based on the monitoring information type, determining key monitoring information of the asset; and Based on the key monitoring information, the usage status information is determined.

3. The method according to claim 2, characterized in that The determining, based on the measurement and control data, the type of monitoring information of the asset includes: Based on the measurement and control data, generating at least one monitoring sequence group; Retrieving a monitoring image of a local area corresponding to the at least one monitoring sequence group; Determining an associated image of the asset based on the surveillance image of the local area; and The monitoring information type of the asset is determined based on the associated image and the at least one monitoring sequence group.

4. The method according to claim 1, characterized in that The use status information includes at least one of an operating state, an apparent state, and a position state. The determining of abnormal assets based on the use status information includes: Based on the monitoring data, determining a retention area of ​​the asset in at least one preset time period; Determining abnormal usage characteristics of the asset based on the usage status information and the monitoring data; and In response to at least one of the retention area and the abnormal usage feature not satisfying a preset condition, the asset is determined to be the abnormal asset.

5. An asset management system, characterized in that: The system includes a monitoring module, an Internet of Things module, a data transmission module and a data processing module, and the data transmission module includes a network management platform; The monitoring module is configured to collect monitoring images of the asset; The IoT module is configured to collect identification data and sensor data; The data transmission module is configured to realize data interaction between the monitoring module, the Internet of Things module and the data processing module, and to realize data interaction between the data processing module and the network management platform; The network management platform is configured to obtain network interaction data; The data processing module is configured as follows: Acquire measurement and control data of assets in the target area, wherein the measurement and control data includes the surveillance images and / or monitoring data, and the assets include at least one of electrical equipment, production and operation equipment, and consumables; Determining usage status information of the asset based on the measurement and control data; Based on the usage status information, determining abnormal assets; as well as The abnormal assets are regulated and managed, and the regulation and management includes regulating operating parameters and / or circulation processes.

6. The system according to claim 5, characterized in that The data processing module is further configured to: Collecting the monitoring image by a monitoring device deployed in at least one local area; Obtaining the network interaction data through the network management platform; Collecting the identification data and the sensor data through the Internet of Things module; as well as generating the monitoring data based on the network interaction data, the identification data and the sensor data; The data processing module is further configured to: Determining the type of monitoring information of the asset based on the measurement and control data; Based on the monitoring information type, determining key monitoring information of the asset; as well as Based on the key monitoring information, the usage status information is determined.

7. The system according to claim 6, characterized in that The data processing module is further configured to: Based on the measurement and control data, generating at least one monitoring sequence group; Retrieving a monitoring image of a local area corresponding to the at least one monitoring sequence group; Determining an associated image of the asset based on the surveillance image of the local area; and The monitoring information type of the asset is determined based on the associated image and the at least one monitoring sequence group.

8. The system according to claim 5, characterized in that The usage status information includes at least one of an operating status, an apparent status, and a position status, and the data processing module is further configured to: Based on the monitoring data, determining a retention area of ​​the asset in at least one preset time period; Determining abnormal usage characteristics of the asset based on the usage status information and the monitoring data; as well as In response to at least one of the retention area and the abnormal usage feature not satisfying a preset condition, the asset is determined to be the abnormal asset.

9. An asset management device, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least part of the computer instructions to implement the asset management method as described in any one of claims 1 to 4.

10. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the asset management method according to any one of claims 1 to 4.

Images