Liquid seasoning manufacturing device and manufacturing method thereof

Abstract

The present invention provides a liquid seasoning manufacturing device and a manufacturing method thereof, wherein the device includes: an equipment monitoring information acquisition subsystem for acquiring equipment monitoring information of a target device on a liquid seasoning manufacturing assembly line; a manufacturing status information determination subsystem for determining manufacturing status information based on the equipment monitoring information; a control template acquisition subsystem for acquiring a control template of a target device; a control strategy determination subsystem for determining a control strategy for a target device based on manufacturing status information and a control template; and a manufacturing subsystem for performing corresponding manufacturing according to the control strategy. A liquid seasoning manufacturing device and a manufacturing method thereof of the present invention determine the manufacturing status information of raw materials based on the equipment monitoring information of a target device on a liquid seasoning manufacturing assembly line; determine the control strategy and control the target device separately based on the control template and manufacturing status information corresponding to the target device, thereby improving the intelligent level of liquid seasoning manufacturing.

Description

Technical Field

[0001] The invention relates to the technical field of seasoning manufacturing, and in particular to a liquid seasoning manufacturing device and a manufacturing method thereof. Background Art

[0002] The traditional manufacturing of liquid condiments (for example, the manufacturing of traditional soy sauce and vinegar) is a traditional process that involves a series of complex steps, including manual bean selection, soaking, steaming, cooling, mixing with flour, koji making and fermentation. Traditional liquid condiment manufacturing mainly relies on manual production, and the production quality of the condiments mainly relies on manual experience to control the quality. The quality is not stable enough, and the production process requires a lot of manpower input and is not smart enough.

[0003] In view of this, there is an urgent need for a liquid seasoning manufacturing device and a manufacturing method thereof to at least solve the above-mentioned shortcomings. Summary of the invention

[0004] One of the purposes of the present invention is to provide a liquid seasoning manufacturing device and a manufacturing method thereof, which determines the manufacturing status information of raw materials inside the target device based on the equipment monitoring information of the target device on the liquid seasoning manufacturing line; determines the control strategy of the target device based on the control template and manufacturing status information corresponding to the target device, and controls the target devices separately according to the control strategy, thereby greatly improving the intelligent level of liquid seasoning manufacturing.

[0005] An embodiment of the present invention provides a liquid seasoning manufacturing device, comprising:

[0006] The equipment monitoring information acquisition subsystem is used to obtain the equipment monitoring information of the target equipment on the liquid seasoning manufacturing line;

[0007] A manufacturing status information determination subsystem is used to determine the manufacturing status information inside the target device based on the device monitoring information;

[0008] A control template acquisition subsystem is used to acquire the control template of the target device;

[0009] A control strategy determination subsystem is used to determine the control strategy of the target equipment according to the manufacturing status information and the control template;

[0010] The manufacturing subsystem is used to carry out the corresponding manufacturing of liquid seasonings on the liquid seasoning manufacturing line according to the control strategy.

[0011] Preferably, the manufacturing status information determination subsystem includes:

[0012] A manufacturing process determination module, used to determine the manufacturing process corresponding to the target device;

[0013] A manufacturing status reading rule determination module is used to determine the manufacturing status reading rule according to the manufacturing process;

[0014] The manufacturing status information reading module is used to read the manufacturing status information according to the equipment monitoring information and the manufacturing status reading rules.

[0015] Preferably, the manufacturing status reading rule determination module includes:

[0016] A feature collection submodule is used to determine an intervention feature set based on a manual manufacturing process record set;

[0017] An intervention intention determination submodule is used to determine the intervention intention according to the intervention feature set;

[0018] A required state information determination submodule is used to determine the required state information according to the intervention intention;

[0019] A monitoring device setting information determination submodule is used to determine the monitoring device setting information;

[0020] A manufacturing status reading rule determination submodule is used to determine the manufacturing status reading rule according to the monitoring equipment setting information and the required status information;

[0021] Among them, the feature collection submodule includes:

[0022] An artificial manufacturing process record acquisition unit, used to acquire an artificial manufacturing process record set corresponding to the manufacturing process;

[0023] A state process axis acquisition unit, used for acquiring a state process axis of a manufacturing process;

[0024] A corresponding relationship determination unit, used to determine one-to-one corresponding manual intervention process points and intervention features according to the manual manufacturing process record set and the state process axis;

[0025] The feature collection unit is used to determine the intervention feature set based on a preset collection rule and according to the point distances between adjacent manual intervention process points.

[0026] Preferably, the intervention intention determination submodule includes:

[0027] An intervention intention reading feature matching unit, used for trying to obtain an intervention intention reading feature according to an intervention feature set and an intervention intention reading feature library;

[0028] an intervention intention reading template acquisition unit, configured to acquire the intervention intention reading template according to a first intervention feature type corresponding to the intervention intention reading feature if the attempt to acquire the intervention intention reading feature is successful;

[0029] An intervention intention first determination unit, configured to determine the intervention intention according to the intervention intention reading template and the intervention intention reading feature;

[0030] a type order determining unit, configured to determine, if an attempt to obtain the intervention intention reading feature fails, an intervention feature type order of a second intervention feature type corresponding to the intervention feature according to the intervention feature set;

[0031] An intervention intention determination process acquisition unit, used to acquire an intervention intention determination process according to the sequence of intervention feature types;

[0032] The second intervention intention determination unit is used to determine the intervention intention according to the intervention intention determination process and the intervention feature set.

[0033] Preferably, the control template acquisition subsystem includes:

[0034] A historical manufacturing status information acquisition module is used to acquire historical manufacturing status information of the manufacturing process corresponding to the target device;

[0035] A historical response decision determination module is used to determine the historical response decision based on the historical manufacturing status information;

[0036] A trigger condition generation module, used to generate trigger conditions according to the monitoring equipment sensing information corresponding to the historical manufacturing status information;

[0037] An application instruction determination module, used to determine the application instruction of the target device according to the historical response decision;

[0038] The instruction association module is used to associate trigger conditions and application instructions to generate control templates.

[0039] Preferably, the application instruction determination module includes:

[0040] A control action library acquisition submodule is used to acquire the control action library of the target device;

[0041] A simulation action sequence determination submodule is used to determine the simulation action sequence of the target device based on historical response decisions;

[0042] The action matching submodule is used to sequentially traverse the simulation actions in the simulation action sequence from the beginning to the end, match the simulation action currently being traversed with the control action in the control action library, and obtain the action matching result;

[0043] The first output submodule is used for outputting the action control instruction corresponding to the successfully matched control action to the application instruction waiting sequence if the action matching result is a successful match;

[0044] The equivalent action set acquisition submodule is used to acquire the equivalent action set of the simulated action that failed to match if the action matching result is a matching failure;

[0045] An equivalent value acquisition submodule is used to obtain equivalent values ​​of equivalent actions in an equivalent action set;

[0046] The second output submodule is used to match the equivalent actions with the control actions in the control action library in descending order of equivalent values, and determine whether there is an action match. If yes, the action control instruction of the corresponding control action is output to the application instruction waiting sequence;

[0047] The application instruction determination submodule is used to determine the application instruction according to the real-time application instruction waiting sequence after the simulation actions in all simulation action sequences are traversed.

[0048] Preferably, the equivalent value acquisition submodule includes:

[0049] A target characteristic information acquisition unit, used to take the simulated action that fails to match as a target simulated action, and acquire target characteristic information of an action target of the target simulated action;

[0050] An equivalent value calculation unit, used for calculating an equivalent value according to the target simulation action, the equivalent action and the target characteristic information;

[0051] The equivalent value calculation unit includes:

[0052] A first simulation result determination subunit is used to perform a first processing simulation according to the target simulation action and the target characteristic information to obtain a first simulation result;

[0053] A second simulation result determination subunit is used to perform a second processing simulation according to the equivalent action and the target characteristic information to obtain a second simulation result;

[0054] A first equivalent value calculation subunit is used to calculate the result similarity between the first simulation result and the second simulation result, and determine the equivalent value according to the result similarity;

[0055] Wherein, the equivalent value calculation unit also includes:

[0056] A mechanism evaluation model acquisition subunit is used to acquire a mechanism evaluation model according to target characteristic information;

[0057] A first evaluation factor determination subunit, for determining a first evaluation factor based on a mechanism evaluation model, according to a target simulation action and an action goal;

[0058] A second evaluation factor determination subunit, for determining a second evaluation factor based on the mechanism evaluation model, according to the equivalent action and the action target;

[0059] The second equivalent value calculation subunit is used to calculate the evaluation factor similarity between the first evaluation factor and the second evaluation factor, and determine the equivalent value according to the evaluation factor similarity.

[0060] An embodiment of the present invention provides a method for producing a liquid seasoning, comprising:

[0061] Step 1: Obtain equipment monitoring information of target equipment on the liquid seasoning manufacturing line;

[0062] Step 2: Determine the manufacturing status information inside the target device based on the device monitoring information;

[0063] Step 3: Get the control template of the target device;

[0064] Step 4: Determine the control strategy of the target equipment based on the manufacturing status information and the control template;

[0065] Step 5: According to the control strategy, the liquid seasoning on the liquid seasoning manufacturing line is manufactured accordingly.

[0066] Preferably, step 2: determining the manufacturing status information inside the target device according to the device monitoring information includes:

[0067] Determine the manufacturing process corresponding to the target device;

[0068] Determine the manufacturing status reading rules according to the manufacturing process;

[0069] Read the manufacturing status information according to the equipment monitoring information and the manufacturing status reading rules.

[0070] Preferably, according to the manufacturing process, the manufacturing status reading rule is determined, including:

[0071] Determine the intervention feature set based on the manual manufacturing process record set;

[0072] Determine intervention intention based on intervention feature set;

[0073] Determine the required status information based on the intervention intention;

[0074] Determine monitoring equipment setting information;

[0075] Determine manufacturing status reading rules based on monitoring equipment setting information and required status information;

[0076] Among them, according to the manual manufacturing process record set, the intervention feature set is determined, including:

[0077] Obtaining a set of manual manufacturing process records corresponding to a manufacturing process;

[0078] Get the status process axis of the manufacturing process;

[0079] According to the manual manufacturing process record set and the state process axis, determine the one-to-one corresponding manual intervention process points and intervention features;

[0080] Based on the preset aggregation rules, the intervention feature set is determined according to the point distances between adjacent manual intervention process points.

[0081] Preferably, determining the intervention intention according to the intervention feature set includes:

[0082] According to the intervention feature set and the intervention intention reading feature library, try to obtain the intervention intention reading feature;

[0083] If the attempt to obtain the intervention intention reading feature is successful, obtaining the intervention intention reading template according to the first intervention feature type corresponding to the intervention intention reading feature;

[0084] Determine the intervention intention according to the intervention intention reading template and the intervention intention reading characteristics;

[0085] If the attempt to obtain the intervention intention reading feature fails, determining the intervention feature type order of the second intervention feature type corresponding to the intervention feature according to the intervention feature set;

[0086] According to the order of intervention feature types, the intervention intention determination process is obtained;

[0087] Determine the process and intervention feature set based on the intervention intention to determine the intervention intention.

[0088] Preferably, step 3: obtaining a control template of the target device includes:

[0089] Obtain historical manufacturing status information of the manufacturing process corresponding to the target device;

[0090] Determine historical response decisions based on historical manufacturing status information;

[0091] Generate trigger conditions based on the monitoring equipment sensing information corresponding to the historical manufacturing status information;

[0092] Determine application instructions for target devices based on historical response decisions;

[0093] Associate trigger conditions and application instructions to generate control templates.

[0094] The beneficial effects of the present invention are:

[0095] The present invention determines the manufacturing status information of the raw materials inside the target equipment based on the equipment monitoring information of the target equipment on the liquid seasoning manufacturing line; determines the control strategy of the target equipment based on the control template and manufacturing status information corresponding to the target equipment, and controls the target equipment respectively according to the control strategy, thereby greatly improving the intelligent level of liquid seasoning manufacturing.

[0096] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the present application documents.

[0097] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0099] Figure 1 is a schematic diagram of a liquid seasoning manufacturing device according to an embodiment of the present invention;

[0100] Figure 2 Schematic diagram of a method for producing a liquid seasoning in an embodiment of the present invention. DETAILED DESCRIPTION

[0101] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0102] The embodiment of the present invention provides a liquid seasoning manufacturing device, such as Figure 1 As shown, including:

[0103] The equipment monitoring information acquisition subsystem 1 is used to acquire the equipment monitoring information of the target equipment on the liquid seasoning manufacturing line; wherein the liquid seasoning manufacturing line is, for example, a manufacturing line for liquid seasonings such as soy sauce and vinegar; the target equipment is: various equipment used for liquid seasoning manufacturing on the liquid seasoning manufacturing line, such as fermentation containers, cooking equipment, cooling equipment, mixing equipment, filtering equipment, and storage containers; the equipment monitoring information is: the equipment operation status information about the target equipment collected by sensors and monitoring systems, such as: real-time monitoring of pH value changes in the fermentation container by an online pH sensor, and another example: real-time monitoring of mixing abnormalities by acquiring mixing pictures through monitoring cameras;

[0104] The manufacturing status information determination subsystem 2 is used to determine the manufacturing status information inside the target device according to the device monitoring information; wherein the manufacturing status information is: the status of the manufacturing raw materials in the target device, for example: the pH is too low and is not suitable for raw material fermentation;

[0105] The control template acquisition subsystem 3 is used to acquire the control template of the target device; wherein the control template is the control logic of the control terminal of the target device, and the control logic includes a plurality of pre-selected states and corresponding pre-selected control strategies in the target device, for example: if the pre-selected state is that the pH value of the fermentation liquid has not reached the ideal range, then the corresponding pre-selected control strategy is: continue fermentation; if the pre-selected state is that the pH value of the fermentation liquid reaches the ideal range, then the corresponding pre-selected control strategy is: enter the next process of the fermentation process;

[0106] The control strategy determination subsystem 4 is used to determine the control strategy of the target device according to the manufacturing state information and the control template; when determining the control strategy of the target device, the manufacturing state information and the pre-selected state are matched, and the pre-selected control strategy corresponding to the pre-selected state that matches the match is used as the immediate control strategy;

[0107] The manufacturing subsystem 5 is used to manufacture the liquid seasoning on the liquid seasoning manufacturing assembly line according to the control strategy. When the liquid seasoning on the liquid seasoning manufacturing assembly line is manufactured according to the control strategy, a remote control instruction of a target device corresponding to the control strategy is determined, and the liquid seasoning on the liquid seasoning manufacturing assembly line is manufactured according to the remote control instruction.

[0108] The working principle and beneficial effects of the above technical solution are:

[0109] The present invention determines the manufacturing status information of the raw materials inside the target equipment based on the equipment monitoring information of the target equipment on the liquid seasoning manufacturing line; determines the control strategy of the target equipment based on the control template and manufacturing status information corresponding to the target equipment, and controls the target equipment respectively according to the control strategy, thereby greatly improving the intelligent level of liquid seasoning manufacturing.

[0110] In one embodiment, the manufacturing status information determination subsystem includes:

[0111] The manufacturing process determination module is used to determine the manufacturing process corresponding to the target device; wherein the manufacturing process is: the local process of the target device corresponding to the entire liquid seasoning manufacturing process, for example: if the target device is a fermentation container, the corresponding manufacturing process is the fermentation process;

[0112] The manufacturing status reading rule determination module is used to determine the manufacturing status reading rule according to the manufacturing process; wherein the manufacturing status reading rule is: a rule for determining the manufacturing status of the seasoning corresponding to the manufacturing process, for example: if the manufacturing process is fermentation, the manufacturing status reading rule is a rule for reading the fermentation status, for example: detecting the pH value of the fermentation solution to determine the fermentation status;

[0113] The manufacturing status information reading module is used to read the manufacturing status information according to the equipment monitoring information and the manufacturing status reading rules.

[0114] The working principle and beneficial effects of the above technical solution are:

[0115] The present invention determines the manufacturing process corresponding to the target device, obtains the manufacturing status reading rule of the manufacturing process, reads the manufacturing status information according to the device monitoring information and the manufacturing status reading rule, and the reading process of the manufacturing status information is more standardized and reasonable.

[0116] In one embodiment, the manufacturing status reading rule determination module includes:

[0117] A feature collection submodule is used to determine an intervention feature set based on a manual manufacturing process record set;

[0118] The intervention intention determination submodule is used to determine the intervention intention according to the intervention feature set; wherein the intervention intention is: the intention of manual intervention, such as: controlling the temperature and humidity of Aspergillus fermentation;

[0119] The required state information determination submodule is used to determine the required state information according to the intervention intention; wherein the required state information is: information in the manufacturing process of the liquid seasoning that needs to be detected, such as: fermentation temperature, fermentation humidity;

[0120] The monitoring device setting information determination submodule is used to determine the monitoring device setting information; wherein the monitoring device setting information is: setting information of various information monitoring devices in the target device, such as: where the temperature and humidity sensors are set;

[0121] The manufacturing status reading rule determination submodule is used to determine the manufacturing status reading rule according to the monitoring device setting information and the required status information; wherein the manufacturing status reading rule is: the monitoring device to be read and the reading content, such as: reading the temperature and humidity data of the temperature and humidity sensor pre-buried in the fermentation liquid;

[0122] Among them, the feature collection submodule includes:

[0123] The artificial manufacturing process record acquisition unit is used to acquire an artificial manufacturing process record set corresponding to the manufacturing process; wherein the artificial manufacturing process record set includes artificial records corresponding to multiple manufacturing processes, such as: records of artificially controlled soy sauce fermentation process;

[0124] A state process axis acquisition unit is used to acquire a state process axis of a manufacturing process; wherein each point on the state process axis corresponds to a process point of a manufacturing process;

[0125] The corresponding relationship determination unit is used to determine the one-to-one corresponding manual intervention process points and intervention features according to the manual manufacturing process record set and the state process axis; wherein the intervention features are intervention information features extracted based on the manual manufacturing process records, including speech semantics (for example, a worker's speech: "I need to turn the song") and behavioral actions (for example, turning the song action), etc.;

[0126] The feature collection unit is used to determine the intervention feature set based on the preset collection rule and the point distance between adjacent manual intervention process points; wherein the preset collection rule is: if the point distance between adjacent manual intervention process points is less than or equal to a preset point distance threshold, the corresponding intervention features are classified into the same intervention feature set, and the preset point distance threshold is set manually in advance.

[0127] The working principle and beneficial effects of the above technical solution are:

[0128] The present invention introduces an artificial manufacturing process record set of the manufacturing process, determines the state process axis corresponding to the manufacturing process; extracts intervention features in the artificial manufacturing process record, and marks them correspondingly on the state process axis; introduces a collection rule to collect the intervention features to obtain an intervention feature set; determines the intervention intention corresponding to the intervention feature set; determines the required state information based on the intervention intention, and the required state information can be used for machine learning to determine whether the current manufacturing process meets the machine intervention conditions; determines the monitoring device setting information of the target device, and determines the monitoring device to be read and the reading content based on the monitoring device setting information and the required state information, that is, the manufacturing state reading rule, thereby improving the accuracy of subsequent manufacturing state reading.

[0129] In one embodiment, the intervention intention determination submodule includes:

[0130] The intervention intention reading feature matching unit is used to try to obtain the intervention intention reading feature according to the intervention feature set and the intervention intention reading feature library; wherein the intervention intention reading feature library stores a plurality of representation features that can directly determine the intervention intention, for example, the semantics corresponding to "prepare to turn the song", the intervention intention can be directly determined as turning the song;

[0131] An intervention intention reading template acquisition unit is used to acquire the intervention intention reading template according to the first intervention feature type corresponding to the intervention intention reading feature if the attempt to acquire the intervention intention reading feature is successful; wherein the first intervention feature type is: a feature type of the intervention intention reading feature, such as: a semantic feature; the intervention intention reading template is, for example: a semantic recognition model;

[0132] An intervention intention first determination unit, configured to determine the intervention intention according to the intervention intention reading template and the intervention intention reading feature;

[0133] A type sequence determination unit is used to determine, if an attempt to obtain the intervention intention reading feature fails, an intervention feature type sequence of a second intervention feature type corresponding to the intervention feature according to the intervention feature set; wherein the second intervention feature type is: a feature type corresponding to the intervention feature in the intervention feature set, such as: a semantic feature, a behavioral feature; and the intervention feature type sequence is: first obtain a feature of a certain intervention feature type, then obtain a feature of a certain intervention feature type, such as: first obtain a semantic feature, then obtain a behavioral feature;

[0134] The intervention intention determination process acquisition unit is used to acquire the intervention intention determination process according to the intervention feature type sequence; wherein the intervention intention determination process is: the process of determining the intervention intention, for example: first determining the possible intervention intention according to the semantic features, and then judging whether the possible intervention intention is executed according to the behavioral features;

[0135] The second intervention intention determination unit is used to determine the intervention intention according to the intervention intention determination process and the intervention feature set.

[0136] The working principle and beneficial effects of the above technical solution are:

[0137] The present invention introduces an intervention intention reading feature library, which stores characterization features that can directly determine the intervention intention. First, the intervention features in the intervention feature set are matched with the intervention features in the intervention intention reading feature library to determine whether the intervention intention can be directly determined. If the match is successful, the determination is made directly; if not, the intervention feature type sequence of the second intervention feature type corresponding to the intervention feature is determined, and the intervention intention determination process is obtained according to the intervention feature type sequence. The intervention intention is determined according to the intervention intention determination process and the intervention feature set. The intervention intention is determined adaptably according to the different characterization degrees of the intervention features, thereby improving the determination efficiency of the intervention intention and further improving the reliability of the subsequent manufacturing status reading rule formulation.

[0138] In one embodiment, the control template acquisition subsystem includes:

[0139] The historical manufacturing status information acquisition module is used to acquire the historical manufacturing status information of the manufacturing process corresponding to the target device; wherein the historical manufacturing status information is: the status of the manufacturing process corresponding to the target device in the historical manufacturing seasoning process, such as: insufficient fermentation;

[0140] The historical response decision determination module is used to determine the historical response decision according to the historical manufacturing status information; wherein the historical response decision is: the solution decision corresponding to the historical manufacturing status information, such as: turning over the song;

[0141] A trigger condition generation module is used to generate a trigger condition based on the monitoring device sensing information corresponding to the historical manufacturing status information; wherein the trigger condition triggers the target device to execute a preset instruction;

[0142] An application instruction determination module is used to determine the application instruction of the target device according to the historical response decision; wherein the application instruction is: a trigger instruction for the target device to execute the historical response decision, for example: if the historical response decision is to turn the song, the corresponding trigger instruction is an instruction to control the target device to execute the turn the song action;

[0143] The instruction association module is used to associate trigger conditions and application instructions to generate control templates.

[0144] The working principle and beneficial effects of the above technical solution are:

[0145] The present invention introduces the manufacturing status of the seasoning that has appeared in history in the manufacturing process corresponding to the target device, and obtains the corresponding historical response decision based on the historical manufacturing status information; determines the trigger condition based on the sensing information of the monitoring device corresponding to the historical manufacturing status information; obtains the application instruction of the target device corresponding to the historical response decision; associates the trigger condition and the application instruction to generate a control template, and the structure of the control template is more reasonable and appropriate.

[0146] In one embodiment, the application instruction determination module includes:

[0147] A control action library acquisition submodule is used to acquire the control action library of the target device; wherein the control action library stores all control actions that can be executed by the target device;

[0148] The simulation action sequence determination submodule is used to determine the simulation action sequence of the target device according to the historical response decision; wherein the simulation action sequence is: the action sequence that the target device should simulate to be performed manually obtained by analyzing the historical response decision;

[0149] The action matching submodule is used to sequentially traverse the simulation actions in the simulation action sequence from the beginning to the end, perform action matching between the simulation action currently being traversed and the control action in the control action library, and obtain the action matching result; wherein the action matching result includes a successful match and a failed match;

[0150] The first output submodule is used for outputting the action control instruction corresponding to the successfully matched control action to the application instruction waiting sequence if the action matching result is a successful match;

[0151] The equivalent action set acquisition submodule is used to acquire the equivalent action set of the simulated action that failed to match if the action matching result is a match failure; wherein the equivalent action set is: a set of alternative actions that control the simulated action that failed to match, for example: the simulated action that failed to match is stirring, and the equivalent action is stirring;

[0152] The equivalent value acquisition submodule is used to obtain the equivalent value of the equivalent action in the equivalent action set; wherein the size of the equivalent value represents the degree to which the equivalent action can replace the simulated action;

[0153] The second output submodule is used to match the equivalent actions with the control actions in the control action library in descending order of equivalent values, and determine whether there is an action match. If yes, the action control instruction of the corresponding control action is output to the application instruction waiting sequence;

[0154] The application instruction determination submodule is used to determine the application instruction according to the real-time application instruction waiting sequence after the simulation actions in all simulation action sequences are traversed.

[0155] The working principle and beneficial effects of the above technical solution are:

[0156] The present invention introduces a control action library of a target device, and at the same time, obtains historical response decisions, analyzes the historical response decisions to obtain a simulation action sequence that the target device should simulate manual execution; traverses the simulation actions in the simulation action sequence, matches the simulation actions being traversed with the control actions in the control action library, and obtains the action matching result. If the action matching is successful, the action control instruction corresponding to the control action is directly output; if the action matching fails, an equivalent action set is introduced to obtain the equivalent value of the equivalent action, and the equivalent actions are matched with the control actions in the control action library in order from large to small in the equivalent value, and the action control instruction of the corresponding control action that meets the action matching is output; when the simulation actions in all simulation action sequences are traversed, the real-time application instruction waiting sequence is determined, and the output of the application instruction is more accurate.

[0157] In one embodiment, the equivalent value acquisition submodule includes:

[0158] The target characteristic information acquisition unit is used to take the simulation action that fails to match as the target simulation action, and acquire the target characteristic information of the action target of the target simulation action; wherein the action target is: the liquid seasoning making raw material in the target device; the target characteristic information is: the attribute information of the action target, such as: fluidity, viscosity and particle shape, etc.;

[0159] An equivalent value calculation unit, used for calculating an equivalent value according to the target simulation action, the equivalent action and the target characteristic information;

[0160] The equivalent value calculation unit includes:

[0161] The first simulation result determination subunit is used to simulate the first processing process according to the target simulation action and the target characteristic information to obtain the first simulation result; wherein the first processing process simulation is: the process of simulating the process of the target simulation action acting on the action target, and the action target generates simulation target parameters based on the target characteristic information; the first simulation result is: the output of the first processing process simulation, including the performance data and state change of the simulated action target under the action of the simulated target simulation action;

[0162] The second simulation result determination subunit is used to simulate the second processing process according to the equivalent action and the target characteristic information to obtain a second simulation result; wherein the second processing process simulation is: a process of simulating the process of the equivalent action acting on the action target; the second simulation result is: an output of the second processing process simulation, including performance data and state changes of the simulated action target under the action of the simulated equivalent action;

[0163] A first equivalent value calculation subunit is used to calculate the result similarity between the first simulation result and the second simulation result, and determine the equivalent value according to the result similarity; wherein the result similarity is the simulation parameter similarity value between the first simulation result and the second simulation result, and the higher the result similarity, the higher the equivalent value, for example, the simulation parameter similarity value is 0.86 and the equivalent value is 86. When determining the equivalent value according to the result similarity, the result similarity is multiplied by a preset constant (for example, 100);

[0164] Wherein, the equivalent value calculation unit also includes:

[0165] The mechanism evaluation model acquisition subunit is used to acquire the mechanism evaluation model according to the target characteristic information; wherein the mechanism evaluation model is: an AI model that analyzes the properties of the action object (such as viscosity, fermentation degree), which is acquired through training based on expert evaluation records of the liquid seasoning production process;

[0166] The first evaluation factor determination subunit is used to determine the first evaluation factor based on the mechanism evaluation model, according to the target simulation action and the action target; wherein the first evaluation factor is: an evaluation vector of the subsequent effect of the target simulation action on the action target;

[0167] A second evaluation factor determination subunit is used to determine a second evaluation factor based on the mechanism evaluation model, according to the equivalent action and the action target; wherein the second evaluation factor is: an evaluation vector of a subsequent effect of the equivalent action acting on the action target;

[0168] The second equivalent value calculation subunit is used to calculate the evaluation factor similarity between the first evaluation factor and the second evaluation factor, and determine the equivalent value according to the evaluation factor similarity. The evaluation factor similarity is: the cosine value of the vector angle between the first evaluation factor and the second evaluation factor. The greater the evaluation factor similarity, the greater the equivalent value. When determining the equivalent value according to the evaluation factor similarity, the evaluation factor similarity is multiplied by a preset constant (for example: 100).

[0169] The working principle and beneficial effects of the above technical solution are:

[0170] The present invention obtains target characteristic information of an action target of a target simulation action, and introduces two methods to calculate an equivalent value based on the target simulation action, the equivalent action and the target characteristic information; the first method uses computer technology to perform simulation, simulates the process of the target simulation action acting on the action target according to the target simulation action and the target characteristic information, determines the performance data and state change of the simulated action target under the action of the target simulation action, obtains a second simulation result corresponding to the equivalent action based on the same technology, calculates the result similarity between the first simulation result and the second simulation result, and determines the equivalent value according to the result similarity; the second method introduces a mechanism evaluation model of the action object, determines a first evaluation factor of the target simulation action and a second evaluation factor of the equivalent action, and determines the equivalent value according to the similarity of the evaluation factors, the calculation accuracy of the equivalent value is higher, and the application suitability of the subsequently determined application instructions is further improved.

[0171] The embodiment of the present invention provides a method for producing a liquid seasoning, such as Figure 2 As shown, including:

[0172] Step 1: Obtain equipment monitoring information of target equipment on the liquid seasoning manufacturing line;

[0173] Step 2: Determine the manufacturing status information inside the target device based on the device monitoring information;

[0174] Step 3: Get the control template of the target device;

[0175] Step 4: Determine the control strategy of the target equipment based on the manufacturing status information and the control template;

[0176] Step 5: According to the control strategy, the liquid seasoning on the liquid seasoning manufacturing line is manufactured accordingly.

[0177] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A liquid seasoning manufacturing device, characterized in that: include: The equipment monitoring information acquisition subsystem is used to obtain the equipment monitoring information of the target equipment on the liquid seasoning manufacturing line; A manufacturing status information determination subsystem is used to determine the manufacturing status information inside the target device based on the device monitoring information; A control template acquisition subsystem is used to acquire the control template of the target device; A control strategy determination subsystem is used to determine the control strategy of the target equipment according to the manufacturing status information and the control template; A manufacturing subsystem, used to manufacture liquid seasonings on a liquid seasoning manufacturing line according to a control strategy; Among them, the control template acquisition subsystem includes: A historical manufacturing status information acquisition module is used to acquire the historical manufacturing status information of the manufacturing process corresponding to the target device; a historical response decision determination module is used to determine the historical response decision based on the historical manufacturing status information; a trigger condition generation module is used to generate a trigger condition based on the monitoring device sensing information corresponding to the historical manufacturing status information; an application instruction determination module is used to determine the application instruction of the target device based on the historical response decision; an instruction association module is used to associate the trigger condition with the application instruction to generate a control template; Among them, the application instruction determination module includes: The control action library acquisition submodule is used to acquire the control action library of the target device; the simulation action sequence determination submodule is used to determine the simulation action sequence of the target device according to the historical response decision; the action matching submodule is used to traverse the simulation actions in the simulation action sequence from the beginning to the end, match the simulation action currently being traversed with the control action in the control action library, and obtain the action matching result; the first output submodule is used to output the action control instruction corresponding to the successfully matched control action to the application instruction waiting sequence if the action matching result is a successful match; the equivalent action set acquisition submodule is used to obtain the equivalent action set of the simulation action that failed to match if the action matching result is a failed match; the equivalent value acquisition submodule is used to obtain the equivalent value of the equivalent action in the equivalent action set; the second output submodule is used to match the equivalent action with the control action in the control action library in the order of equivalent value from large to small, and determine whether there is an action match. If it is met, the action control instruction of the corresponding control action is output to the application instruction waiting sequence; the application instruction determination submodule is used to determine the application instruction according to the real-time application instruction waiting sequence after the simulation actions in all simulation action sequences are traversed; Among them, the equivalent value acquisition submodule includes: a target characteristic information acquisition unit, used to take the simulated action that fails to match as the target simulated action, and acquire the target characteristic information of the action target of the target simulated action; an equivalent value calculation unit, used to calculate the equivalent value according to the target simulated action, the equivalent action and the target characteristic information; The equivalent value calculation unit includes: The first simulation result determination subunit is used to simulate the first processing process according to the target simulation action and the target characteristic information to obtain the first simulation result; the second simulation result determination subunit is used to simulate the second processing process according to the equivalent action and the target characteristic information to obtain the second simulation result; the first equivalent value calculation subunit is used to calculate the result similarity between the first simulation result and the second simulation result, and determine the equivalent value according to the result similarity; or, The equivalent value calculation unit includes: The mechanism evaluation model acquisition subunit is used to acquire the mechanism evaluation model according to the target characteristic information; the first evaluation factor determination subunit is used to determine the first evaluation factor based on the mechanism evaluation model according to the target simulation action and the action target; the second evaluation factor determination subunit is used to determine the second evaluation factor based on the mechanism evaluation model according to the equivalent action and the action target; the second equivalent value calculation subunit is used to calculate the evaluation factor similarity between the first evaluation factor and the second evaluation factor, and determine the equivalent value according to the evaluation factor similarity.

2. A liquid seasoning manufacturing device as claimed in claim 1, characterized in that: The manufacturing status information determination subsystem includes: A manufacturing process determination module, used to determine the manufacturing process corresponding to the target device; A manufacturing status reading rule determination module is used to determine the manufacturing status reading rule according to the manufacturing process; The manufacturing status information reading module is used to read the manufacturing status information according to the equipment monitoring information and the manufacturing status reading rules.

3. A liquid seasoning manufacturing device as claimed in claim 2, characterized in that: The manufacturing status reading rule determination module includes: A feature collection submodule is used to determine an intervention feature set based on a manual manufacturing process record set; An intervention intention determination submodule is used to determine the intervention intention according to the intervention feature set; A required state information determination submodule is used to determine the required state information according to the intervention intention; A monitoring device setting information determination submodule is used to determine the monitoring device setting information; A manufacturing status reading rule determination submodule is used to determine the manufacturing status reading rule according to the monitoring equipment setting information and the required status information; The feature collection submodule includes: An artificial manufacturing process record acquisition unit is used to acquire an artificial manufacturing process record set corresponding to a manufacturing process; a state process axis acquisition unit is used to acquire the state process axis of the manufacturing process; a corresponding relationship determination unit is used to determine one-to-one corresponding artificial intervention process points and intervention features based on the artificial manufacturing process record set and the state process axis; a feature collection unit is used to determine the intervention feature set based on the preset collection rules and the point distance between adjacent artificial intervention process points.

4. A liquid seasoning manufacturing device as claimed in claim 3, characterized in that: The intervention intention determination submodule includes: An intervention intention reading feature matching unit, used for trying to obtain an intervention intention reading feature according to an intervention feature set and an intervention intention reading feature library; an intervention intention reading template acquisition unit, configured to acquire the intervention intention reading template according to a first intervention feature type corresponding to the intervention intention reading feature if the attempt to acquire the intervention intention reading feature is successful; An intervention intention first determination unit, configured to determine the intervention intention according to the intervention intention reading template and the intervention intention reading feature; a type sequence determining unit, configured to determine, if an attempt to obtain the intervention intention reading feature fails, an intervention feature type sequence of a second intervention feature type corresponding to the intervention feature according to the intervention feature set; An intervention intention determination process acquisition unit, used to acquire an intervention intention determination process according to the sequence of intervention feature types; The second intervention intention determination unit is used to determine the intervention intention according to the intervention intention determination process and the intervention feature set.

5. A method for producing a liquid seasoning, characterized in that: include: Step 1: Obtain equipment monitoring information of target equipment on the liquid seasoning manufacturing line; Step 2: Determine the manufacturing status information inside the target device based on the device monitoring information; Step 3: Get the control template of the target device; Step 4: Determine the control strategy of the target equipment based on the manufacturing status information and the control template; Step 5: According to the control strategy, the liquid seasoning on the liquid seasoning manufacturing line is manufactured accordingly; Among them, step 3: obtaining the control template of the target device includes: Obtain historical manufacturing status information of the manufacturing process corresponding to the target device; determine historical response decisions based on the historical manufacturing status information; generate trigger conditions based on the sensing information of the monitoring device corresponding to the historical manufacturing status information; determine application instructions of the target device based on the historical response decisions; associate the trigger conditions and application instructions to generate a control template; Among them, the application instructions of the target device are determined according to the historical response decisions, including: Obtain the control action library of the target device; determine the simulation action sequence of the target device based on historical response decisions; traverse the simulation actions in the simulation action sequence from beginning to end, match the simulation action currently being traversed with the control action in the control action library, and obtain the action matching result; if the action matching result is a successful match, output the action control instruction corresponding to the successfully matched control action to the application instruction waiting sequence; if the action matching result is a failed match, obtain the equivalent action set of the simulation action that failed to match; obtain the equivalent value of the equivalent action in the equivalent action set; match the equivalent action with the control action in the control action library in order from large to small in terms of equivalent value, and determine whether there is an action match. If yes, output the action control instruction of the corresponding control action to the application instruction waiting sequence; when the simulation actions in all simulation action sequences are traversed, determine the application instruction according to the real-time application instruction waiting sequence; Wherein, obtaining the equivalent value of the equivalent action in the equivalent action set includes: Taking the simulated action that fails to match as the target simulated action, obtaining the target characteristic information of the action target of the target simulated action; calculating the equivalent value according to the target simulated action, the equivalent action and the target characteristic information; Among them, according to the target simulation action, the equivalent action and the target characteristic information, the equivalent value is calculated, including: Perform a first processing simulation according to the target simulation action and the target characteristic information to obtain a first simulation result; perform a second processing simulation according to the equivalent action and the target characteristic information to obtain a second simulation result; calculate the result similarity of the first simulation result and the second simulation result, and determine the equivalent value according to the result similarity; or, Among them, according to the target simulation action, the equivalent action and the target characteristic information, the equivalent value is calculated, including: According to the target characteristic information, a mechanism evaluation model is obtained; based on the mechanism evaluation model, a first evaluation factor is determined according to the target simulation action and the action target; based on the mechanism evaluation model, a second evaluation factor is determined according to the equivalent action and the action target; the evaluation factor similarity between the first evaluation factor and the second evaluation factor is calculated, and the equivalent value is determined according to the evaluation factor similarity.

6. A method for producing a liquid seasoning as claimed in claim 5, characterized in that: Step 2: Determine the manufacturing status information inside the target device based on the device monitoring information, including: Determine the manufacturing process corresponding to the target device; Determine the manufacturing status reading rules according to the manufacturing process; Read the manufacturing status information according to the equipment monitoring information and the manufacturing status reading rules.

7. A method for producing a liquid seasoning according to claim 6, characterized in that: According to the manufacturing process, determine the manufacturing status reading rules, including: Determine the intervention feature set based on the manual manufacturing process record set; Determine intervention intention based on intervention feature set; Determine the required status information based on the intervention intention; Determine monitoring equipment setting information; Determine manufacturing status reading rules based on monitoring equipment setting information and required status information; Among them, according to the manual manufacturing process record set, the intervention feature set is determined, including: Obtain an artificial manufacturing process record set corresponding to the manufacturing process; obtain a state process axis of the manufacturing process; determine one-to-one corresponding artificial intervention process points and intervention features based on the artificial manufacturing process record set and the state process axis; determine an intervention feature set based on the point distance between adjacent artificial intervention process points based on a preset aggregation rule.

8. A method for producing a liquid seasoning according to claim 7, characterized in that: Based on the intervention feature set, determine the intervention intention, including: According to the intervention feature set and the intervention intention reading feature library, try to obtain the intervention intention reading feature; If the attempt to obtain the intervention intention reading feature is successful, obtaining the intervention intention reading template according to the first intervention feature type corresponding to the intervention intention reading feature; Determine the intervention intention according to the intervention intention reading template and the intervention intention reading characteristics; If the attempt to obtain the intervention intention reading feature fails, determining the intervention feature type order of the second intervention feature type corresponding to the intervention feature according to the intervention feature set; According to the order of intervention feature types, the intervention intention determination process is obtained; Determine the process and intervention feature set based on the intervention intention to determine the intervention intention.

Images