Article quality digital quantification method based on multi-dimensional environment perception and dynamic weighting

Abstract

The disclosure is a kind of based on multi-dimensional environment perception and dynamic weighting article quality digital quantification method, comprising: synchronously real-time acquisition of the physical state data of the measured article and the environment characteristic data of the environment where the measured article is located;The feature comparison of the real-time collected environment characteristic data and the scene model database is carried out to identify the environment scene type where the current measured article is located, and the quality weight coefficient corresponding to the environment scene type is obtained;Dynamic weighting and quality fusion calculation obtains the real-time quality total index of the measured article;End side solidification and offline output.This embodiment combines multi-dimensional environment characteristics and article physical state to do correlation verification, distinguishes effective behavior and invalid behavior through scene matching dynamic weight, eliminates data distortion and cheating problem, and truly restores article quality;Adopt multi-dimensional feature fusion weighting algorithm, follow the objective law of article growth, aging, etc., no longer simply superimpose single index, make the quantification result fit the actual value of article.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method for digitally quantifying the quality of goods based on multidimensional environmental perception and dynamic weighting. Background Technology

[0002] With the development of modern supply chain management, smart logistics, and traceability technologies, higher demands are being placed on the quality control of high-value goods (such as high-end agricultural products, cold chain pharmaceuticals, precision instruments, aged foods, and luxury goods) throughout their entire lifecycle, from production and warehousing to transportation and sales. Traditional quality control models are gradually shifting from "end-point inspection" to "process monitoring." However, existing product monitoring and traceability technologies still face numerous technical bottlenecks and shortcomings in practical applications, specifically in the following aspects: 1. Single-dimensional condition monitoring lacks correlation verification of multi-source environmental features, making it difficult to achieve high-precision process quality quantification. Existing IoT monitoring devices typically rely on a single type of sensor (such as an accelerometer or thermometer) to record the physical state data of objects. This isolated method of recording physical quantities has a serious logical flaw: it ignores the decisive influence of the "environmental context" on the value of the data, making it impossible to distinguish the true quality differences behind similar physical signals. Take the quantification of livestock quality as an example: its core commercial value lies in the "effective amount of movement" of an individual animal in a natural outdoor environment. However, existing electronic ear tags or leg bands can only mechanically record acceleration or steps, failing to perceive the environmental context of the livestock's movement. This leads to loopholes in "data fraud" and "evaluation distortion": livestock restlessness in confined cages, passive jolting in transport vehicles, and even regular vibrations generated by the use of mechanical stepping devices can all be recorded as high step counts by sensors. Due to the lack of synchronous perception and weighted correlation of environmental lighting characteristics or spatial features, existing technology cannot effectively separate high-value "ecological free-range movement" from low-value "penning / stress / cheating vibrations." Monitoring data lacking environmental dimension verification cannot truly reflect the final quality level of an object.

[0003] 2. The lack of a fusion calculation model based on multi-dimensional physical characteristics makes it difficult for quality evaluation results to reflect the true value of the items. High quality is often the result of the synergistic effect of multiple physical factors, rather than a simple sum of a single indicator. Existing monitoring technologies typically employ isolated data recording methods and lack a mechanism to integrate and calculate physical characteristics of different dimensions (such as "movement frequency" and "environmental energy input"), resulting in significant "value distortion" in the final quality data.

[0004] Taking livestock quality quantification as an example, the biological value of high-quality free-range livestock depends not only on the magnitude of their exercise but also on whether that exercise occurs in a natural environment conducive to growth. For instance, the biological value accumulated from walking outdoors in bright sunlight (such as promoting calcium absorption and firming meat) is far greater in biological evaluation than the value of forced exercise in dark and damp environments. Current technologies, lacking dynamic weighting algorithms based on "light-motion synergy" or "energy-action coupling," treat physical state data from different environmental backgrounds as equivalent. This dimension-deficient evaluation model, while accurate in numerical recording, lacks authenticity in quality characterization, failing to present the end-user with the true growth process and intrinsic value of the product.

[0005] 3. The data processing of the "centralized post-processing" architecture is lagging behind and cannot meet the requirements of real-time quality quantification on the edge. Current quality assessment systems generally adopt an architecture of "terminal data collection - network upload - server analysis." This model separates data collection from quality calculation in time and space. On the one hand, the continuous transmission of massive amounts of raw sensor logs instead of calculated quality conclusions wastes communication resources and energy. On the other hand, for items in offline environments (such as remote pastures or during cold chain transportation), the lack of independent computing power and embedded evaluation models at the edge makes it impossible to generate and store the current quality level locally in real time. This results in the inability of relevant parties to directly read and confirm the current cumulative quality status of items during the circulation process without relying on a backend network connection.

[0006] 4. The discontinuity of energy during the monitoring cycle affects the integrity of the quality accumulation algorithm. For items with long growth or storage cycles (such as large livestock raised for several years or fermented foods requiring long-term aging), quality formation is a continuous integral process. Current technologies largely rely on fixed-capacity batteries, making it difficult to support high-frequency sampling and continuous monitoring throughout the entire lifecycle. Once the battery is depleted or the equipment needs to be replaced midway, the input to the quality accumulation algorithm is interrupted, resulting in the final output "total lifecycle quality index" lacking complete time-series support, thus reducing the scientific validity and reference value of the quantitative results.

[0007] Therefore, it is necessary to improve one or more of the problems existing in the above-mentioned related technical solutions.

[0008] It should be noted that this section is intended to provide background or context for the technical solutions of this disclosure as set forth in the claims. The description herein does not constitute an admission that it is prior art simply because it is included in this section. Summary of the Invention

[0009] The purpose of this invention is to provide a method for digitally quantifying the quality of goods based on multi-dimensional environmental perception and dynamic weighting, thereby overcoming, to at least some extent, one or more problems caused by the limitations and defects of related technologies.

[0010] This invention first provides a method for digitally quantifying the quality of goods based on multi-dimensional environmental perception and dynamic weighting, including: S1, Multi-dimensional Feature Synchronous Acquisition: Synchronously and in real time acquires the physical state data of the test item and the environmental feature data of the environment in which the test item is located; S2, Scene Recognition and Weight Matching: The preset scene model database and the quality weight coefficients corresponding to each environmental scene type are used to compare the real-time collected environmental feature data with the scene model database to identify the environmental scene type of the current test item and obtain the quality weight coefficients corresponding to that environmental scene type. S3, Dynamic weighted and quality fusion calculation: The acquired physical state data and quality weight coefficients are weighted and fused to generate the process quality score of the current time segment, and the process quality score is integrated or accumulated over the time series to obtain the real-time total quality index of the item under test. S4, End-side solidification and offline output: The calculated real-time total quality index and its corresponding process data are solidified, and the real-time total quality index is output offline through a near-field communication device.

[0011] In this invention, in S1, the physical state data includes at least one of acceleration, angular velocity, displacement, vibration frequency, and resting time.

[0012] In this invention, in S1, the environmental characteristic data includes at least one of light radiation intensity, ambient temperature gradient, mechanical vibration energy spectrum, and electromagnetic field intensity.

[0013] In this invention, a monitoring terminal is attached to the object to be tested. In step S1, the method for obtaining environmental characteristic data of the environment in which the object to be tested is located includes: directly mapping the environmental characteristic data through the electrical output characteristics of the energy harvesting unit on the monitoring terminal.

[0014] In this invention, in S2, the quality weighting coefficient is a pre-set quantitative parameter based on biological growth laws or physicochemical aging laws, used to define the positive or negative value contribution of different environmental scenarios to the physical state data.

[0015] In this invention, in S3, the weighted fusion calculation is a weighted summation calculation.

[0016] The present invention further provides a digital quantification system for product quality based on multi-dimensional environmental perception and dynamic weighting, the system comprising: The multi-dimensional feature synchronous acquisition module is used to synchronously and in real time acquire the physical state data of the test object and the environmental feature data of the environment in which the test object is located; The scene recognition and weight matching module is used to preset the scene model database and the quality weight coefficients corresponding to each environmental scene type. It compares the real-time collected environmental feature data with the scene model database to identify the environmental scene type of the current test item and obtain the quality weight coefficients corresponding to that environmental scene type. The dynamic weighted and quality fusion calculation module is used to perform weighted fusion calculation on the acquired physical state data and quality weight coefficients to generate the process quality score of the current time segment, and integrate or accumulate the process quality score over the time series to obtain the real-time total quality index of the item under test. The end-side solidification and offline output module is used to solidify the calculated real-time total quality index and its corresponding process data, and output the real-time total quality index offline through a near-field communication device.

[0017] The technical solution provided by this invention may include the following beneficial effects: This invention presents a digital quantification method for item quality based on multidimensional environmental perception and dynamic weighting. It combines multidimensional environmental features with the physical state of the item for correlation verification, and distinguishes between valid and invalid behaviors through scene matching and dynamic weighting, thereby eliminating data distortion and cheating issues and truly restoring the quality of the item. It adopts a multidimensional feature fusion weighting algorithm, which follows the objective laws of item growth and aging, and no longer simply adds a single indicator, so that the quantification results are consistent with the actual value of the item. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0019] Figure 1 A flowchart illustrating the method for digital quantification of item quality based on multi-dimensional environmental perception and dynamic weighting in an exemplary embodiment of this disclosure is shown. Figure 2 This diagram illustrates a process flow chart for a method of quantifying the quality of free-range poultry throughout its entire life cycle, as described in Embodiment 1 of this disclosure. Detailed Implementation

[0020] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0021] Furthermore, the accompanying drawings are merely illustrative diagrams of embodiments of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities.

[0022] This example implementation first provides a method for digitally quantifying item quality based on multi-dimensional environmental perception and dynamic weighting. Please refer to [reference needed]. Figure 1 This method may include: S1-S4, as follows: S1, Multi-dimensional Feature Synchronous Acquisition: Synchronously and in real time acquires the physical state data of the test item and the environmental feature data of the environment in which the test item is located; S2, Scene Recognition and Weight Matching: The preset scene model database and the quality weight coefficients corresponding to each environmental scene type are used to compare the real-time collected environmental feature data with the scene model database to identify the environmental scene type of the current test item and obtain the quality weight coefficients corresponding to that environmental scene type. S3, Dynamic weighted and quality fusion calculation: The acquired physical state data and quality weight coefficients are weighted and fused to generate the process quality score of the current time segment, and the process quality score is integrated or accumulated over the time series to obtain the real-time total quality index of the item under test. S4, End-side solidification and offline output: The calculated real-time total quality index and its corresponding process data are solidified, and the real-time total quality index is output offline through a near-field communication device.

[0023] In this embodiment, multi-dimensional environmental features and the physical state of the item are combined for correlation verification. By using scene matching and dynamic weights, valid and invalid behaviors are distinguished to prevent data distortion and cheating, and to truly restore the quality of the item. A multi-dimensional feature fusion weighting algorithm is adopted to follow the objective laws of item growth and aging, rather than simply adding a single indicator, so that the quantitative results are consistent with the actual value of the item.

[0024] The specific process of each step in the above embodiments will be described below.

[0025] In S1, physical state data of the object under test and environmental characteristic data of the environment in which the object is located are synchronously collected according to a preset sampling frequency. The physical state data characterizes the dynamic state or physical state of the object and includes at least one of acceleration, angular velocity, displacement, vibration frequency, and static duration. The environmental characteristic data characterizes the external physical field characteristics of the object and includes at least one of light radiation intensity, ambient temperature gradient, mechanical vibration energy spectrum, and electromagnetic field intensity.

[0026] The environmental feature data is acquired using an "energy-sensor multiplexing" method. Specifically, a monitoring terminal is attached to the object to be tested, and the environmental feature data is directly mapped by the electrical output characteristics (such as open-circuit voltage, short-circuit current, or pulse frequency) of the energy harvesting unit (such as photovoltaic module, thermoelectric generator module, or piezoelectric module) on the monitoring terminal. This eliminates the need for a separate environmental sensor and enables the simultaneous acquisition of energy and perception of the environment.

[0027] In S2, the scene model database includes at least two opposing scene models: one is a high-value scene model, which corresponds to the optimal growth or storage environment of an item (e.g., suitable lighting, constant temperature and stillness) and is associated with a positive high-weight coefficient; the other is a low-value or abnormal scene model, which corresponds to the poor growth or damaged environment of an item (e.g., claustrophobic darkness, violent unnatural vibration) and is associated with a low-weight coefficient or a negative penalty coefficient.

[0028] The quality weighting coefficient is a pre-set quantitative parameter based on biological growth laws or physicochemical aging laws, used to define the positive or negative value contribution of different environmental scenarios to the physical state data. For example, when identified as a "natural light / outdoor" scenario, a high weighting coefficient is matched, and when identified as a "dark light / confined space" scenario, a low weighting coefficient or a zero weighting coefficient is matched.

[0029] In S3, the computational logic of the multidimensional weighted fusion algorithm follows the principle that the accumulation of physical states in high-value environments is better than that in low-value environments, so as to achieve value classification of physical data.

[0030] In S4, the monitoring terminal is attached to the item to be tested. The calculated real-time overall quality index and the corresponding key process data are digitally signed inside the monitoring terminal and written into the local non-volatile secure storage unit. Through the near field communication (NFC) interface or low power short-range communication interface, without the need to connect to a wide area network, it responds to the reading request of the external inspection device to output the signed quality evaluation result.

[0031] The following specific embodiments further illustrate the digital quantification method for item quality based on multi-dimensional environmental perception and dynamic weighting of this application.

[0032] Example 1: Implementation of a Whole-life Cycle Quality Quantification Method for Free-range Poultry Please refer to Figure 2 , this example describes the specific process of applying the method of the present invention to the digital quantification of the quality of free-range poultry. This method runs in a foot-ring monitoring terminal worn on the foot of the poultry.

[0033] Step 1: Implementation of multi-dimensional feature synchronous acquisition.

[0034] Physical state data acquisition: A low-power three-axis acceleration sensor is built into the foot-ring monitoring terminal. The microcontroller unit (MCU) of the monitoring terminal samples the acceleration data at a frequency of 25 Hz, and through the built-in step-counting algorithm, converts the acceleration sequence that conforms to the biomechanical characteristics of poultry walking into the effective number of steps (N). For example, by judging the vibration frequency of the collected acceleration sequence, when the frequency is between 0.5 and 3 Hz, it is determined to conform to the normal walking characteristics of poultry and is included in the effective number of steps; if the frequency is not within this range (such as high-frequency mechanical jitter or cheating shakes), it is determined as invalid data and discarded.

[0035] Environmental feature data acquisition (energy-sensing multiplexing): A flexible amorphous silicon thin-film solar cell is integrated on the surface of the foot-ring monitoring terminal. This cell serves both as the energy source of the system and as a sensing device for environmental light intensity. The MCU measures the open-circuit voltage (V) of the solar cell periodically (for example, every 10 minutes) through its analog-to-digital conversion pin. Since V is positively correlated with the light radiation intensity, the voltage value is directly used as environmental feature data to characterize the light level of the environment where the poultry is located.

[0036] Step 2: Implementation of scene recognition and weight matching.

[0037] A scene model database based on light voltage is pre-set in the firmware of the monitoring terminal, specifically a set of voltage thresholds Vth: High-value scene model (outdoor high light): When V > 1.8 volts, the MCU determines that the current is an "outdoor high light" scene. The movement in this scene is regarded as the ecological movement with the highest value, and the quality weight coefficient K_outdoor = 1.5 is matched.

[0038] Medium-value scene model (indoor / cloudy day): When 0.5 volts < V ≤ 1.8 volts, the MCU determines that the current is an "indoor / cloudy day" scene. The movement value in this scene is relatively low, and the quality weight coefficient K_indoor = 0.8 is matched.

[0039] Low-value scenario model (night / dark): When V ≤ 0.5 volts, the MCU determines that the current scenario is "night / dark". The steps generated in this scenario are likely to be invalid vibrations or stress responses, with extremely low value, and the matching quality weight coefficient K_dark = 0.1.

[0040] Step 3: Implementation of dynamic weighted and quality-integrated calculation.

[0041] The MCU performs a quality fusion calculation once every preset period. Within that period, it calculates the process quality score Score_period by weighting and summing the accumulated steps N_outdoor (steps in bright outdoor light), N_indoor (steps indoors / under cloudy weather), and N_dark (steps at night / in darkness) under different scenarios with their corresponding weighting coefficients.

[0042] Score_period=(N_outdoor×K_outdoor)+(N_indoor×K_indoor)+(N_dark×K_dark) Meanwhile, assuming that free-range poultry has an initial total quality index Q_initial, the MCU maintains a total quality index Q_total stored in non-volatile memory throughout the entire life cycle and accumulates it: Q_total = Q_initial + Score_period.

[0043] Step 4: Implementation of end-side solidification and offline output.

[0044] Data persistence: At the end of each computation cycle, the MCU performs a chained hash operation on the data packet containing {timestamp, Score_period, Q_total} and the hash value of the data packet from the previous cycle to generate a hash digest of the current data block. Subsequently, the MCU calls its built-in hardware encryption engine and uses a private key stored in a one-time programmable area (which cannot be exported) to sign the hash digest using an elliptic curve digital signature algorithm. The signed data packet is then written to the local Flash memory.

[0045] Offline output: When a consumer brings an NFC-enabled smartphone close to the ankle bracelet, the NFC chip in the terminal is activated, transmitting the stored historical data packets and public key to the phone. The mobile app then uses the public key to verify the signature locally. If the verification is successful, it parses and displays quantitative information such as the poultry's overall quality index throughout its entire life cycle and daily outdoor activity time.

[0046] Among them, the total life-cycle quality index obtained by accumulation can also be used as a basis. Figure 2In this system, the total lifecycle score (Q_total) is used to classify different quality standards. For example, when the total lifecycle quality index is greater than standard A, the output is identified as "Special Grade"; when the total lifecycle quality index is not greater than standard A but greater than standard B, the output is identified as "Excellent Grade".

[0047] Example 2: Implementation of a method for quantifying the storage environment quality of aged foods (such as Pu-erh tea cakes) This embodiment describes the quantitative process of applying the method of the present invention to the quality deterioration or appreciation of statically aged items, which is carried out within a thin monitoring label affixed to the packaging of Pu'er tea cakes.

[0048] Step 1: Implementation of synchronous acquisition of multi-dimensional features.

[0049] Physical state data acquisition: For statically aged items, the core physical state is the "aging time". The MCU uses an internal real-time clock to accurately measure the time increment Δt, which is the physical state data in this embodiment.

[0050] Environmental characteristic data acquisition: The monitoring tag integrates a high-precision temperature and humidity sensor to collect ambient temperature T and relative humidity H as environmental characteristic data.

[0051] Step 2: Implementation of scene recognition and weight matching.

[0052] The monitoring tag includes a pre-set temperature and humidity scenario model for the aging of Pu'er tea: High-value scenario model (ideal aging zone): When 20°C≤T≤30°C and 55%≤H≤75%, the MCU determines it as an "ideal aging" scenario and matches the positive quality weight coefficient K_ideal=+1.0.

[0053] Low-value scenario model (temperature and humidity deviation zone): When the temperature or humidity deviates slightly from the ideal range (e.g., 30°C < T ≤ 40°C and 75% < H ≤ 90%), a lower positive weight coefficient is matched, such as K_deviation = +0.2.

[0054] Negative Value Scenario Model (Quality Deterioration Zone): When T>40°C or H>90%, the MCU determines it as a "high temperature and high humidity deterioration" scenario. This environment will accelerate the mold growth of tea leaves, and a negative penalty weight coefficient K_damage=-5.0 is matched.

[0055] Step 3: Implementation of dynamic weighted and quality-integrated calculation.

[0056] The MCU calculates the quality score for each day based on the different scenarios and their duration. Assume the tea cake has an initial overall quality index Q_initial.

[0057] Daily quality change Score_day = Σ(Δt_scene × K_scene) Where Δt_scene represents the duration of time spent in a certain scene on a given day, and K_scene represents the weight corresponding to that scene.

[0058] The total quality index throughout the entire product lifecycle is Q_total = Q_initial + Score_day. If the product remains in a deterioration zone for an extended period, Q_total will decrease significantly.

[0059] Step 4: Implementation of end-side solidification and offline output.

[0060] Similar to Example 1, the daily calculated overall quality index and environmental summary data are digitally signed and stored in a chain-like structure in the tag's local memory. Users can use an NFC-enabled mobile phone to read the complete storage environment history of the tea cake since it left the factory and its current quality rating index at any time, and verify the authenticity and completeness of the data offline.

[0061] This application also has the following beneficial effects: Achieve real-time offline computing on the edge: Abandoning the traditional centralized backend processing mode, calculation and storage are completed locally on the monitoring terminal without relying on a wide area network. It supports real-time offline viewing of quality data, while reducing massive amounts of raw data transmission and saving communication and equipment energy consumption; Ensure data integrity throughout the entire life cycle: Adopting an energy-sensor multiplexing design, relying on the energy harvesting unit for self-powered operation, coupled with local non-volatile storage and data signature, it significantly reduces the risk of power outages and ensures that the accumulated quality data throughout the entire life cycle is continuous, complete, traceable, and tamper-proof.

[0062] This disclosure also provides a digital quantification system for product quality based on multi-dimensional environmental perception and dynamic weighting, the system comprising: The multi-dimensional feature synchronous acquisition module is used to synchronously and in real time acquire the physical state data of the test object and the environmental feature data of the environment in which the test object is located; The scene recognition and weight matching module is used to preset the scene model database and the quality weight coefficients corresponding to each environmental scene type. It compares the real-time collected environmental feature data with the scene model database to identify the environmental scene type of the current test item and obtain the quality weight coefficients corresponding to that environmental scene type. The dynamic weighted and quality fusion calculation module is used to perform weighted fusion calculation on the acquired physical state data and quality weight coefficients to generate the process quality score of the current time segment, and integrate or accumulate the process quality score over the time series to obtain the real-time total quality index of the item under test. The end-side solidification and offline output module is used to solidify the calculated real-time total quality index and its corresponding process data, and output the real-time total quality index offline through a near-field communication device.

[0063] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0064] It should be noted that although several modules of the system for executing actions are mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided into multiple modules for embodiment. Components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the present invention according to actual needs. Those skilled in the art can understand and implement this without any inventive effort.

[0065] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

[0066] It should be noted that the installation of image acquisition and personal identification equipment in public places involved in this application is necessary for maintaining public safety, complies with relevant national regulations, and is accompanied by prominent warning signs. The collected personal images and identification information can only be used for the purpose of maintaining public safety and not for other purposes; or the images, personal identification data, etc. in this application are all legally and compliantly obtained or collected with the individual's separate consent.

Claims

1. A method for digitally quantifying the quality of goods based on multi-dimensional environmental perception and dynamic weighting, characterized in that, include: S1, Multi-dimensional Feature Synchronous Acquisition: Synchronously and in real time acquires the physical state data of the test item and the environmental feature data of the environment in which the test item is located; S2, Scene Recognition and Weight Matching: The preset scene model database and the quality weight coefficients corresponding to each environmental scene type are used to compare the real-time collected environmental feature data with the scene model database to identify the environmental scene type of the current test item and obtain the quality weight coefficients corresponding to that environmental scene type. S3, Dynamic weighted and quality fusion calculation: The acquired physical state data and quality weight coefficients are weighted and fused to generate the process quality score of the current time segment, and the process quality score is integrated or accumulated over the time series to obtain the real-time total quality index of the item under test. S4, End-side solidification and offline output: The calculated real-time total quality index and its corresponding process data are solidified, and the real-time total quality index is output offline through a near-field communication device.

2. The method for digital quantification of product quality based on multi-dimensional environmental perception and dynamic weighting according to claim 1, characterized in that, In S1, the physical state data includes at least one of acceleration, angular velocity, displacement, vibration frequency, and resting time.

3. The method for digital quantification of product quality based on multi-dimensional environmental perception and dynamic weighting according to claim 1, characterized in that, In S1, the environmental characteristic data includes at least one of light radiation intensity, ambient temperature gradient, mechanical vibration energy spectrum, and electromagnetic field intensity.

4. The method for digital quantification of product quality based on multi-dimensional environmental perception and dynamic weighting according to claim 1, characterized in that, In step S1, a monitoring terminal is attached to the object to be tested. The method for obtaining environmental characteristic data of the environment in which the object to be tested is located includes: directly mapping the environmental characteristic data through the electrical output characteristics of the energy harvesting unit on the monitoring terminal.

5. The method for digital quantification of product quality based on multi-dimensional environmental perception and dynamic weighting according to claim 1, characterized in that, In S2, the quality weighting coefficient is a quantitative parameter pre-set based on biological growth laws or physicochemical aging laws, used to define the positive or negative value contribution of different environmental scenarios to the physical state data.

6. The method for digital quantification of product quality based on multi-dimensional environmental perception and dynamic weighting according to claim 1, characterized in that, In S3, the weighted fusion calculation is a weighted summation calculation.

7. A digital quantification system for product quality based on multi-dimensional environmental perception and dynamic weighting, characterized in that: The system includes: The multi-dimensional feature synchronous acquisition module is used to synchronously and in real time acquire the physical state data of the test object and the environmental feature data of the environment in which the test object is located; The scene recognition and weight matching module is used to preset the scene model database and the quality weight coefficients corresponding to each environmental scene type. It compares the real-time collected environmental feature data with the scene model database to identify the environmental scene type of the current test item and obtain the quality weight coefficients corresponding to that environmental scene type. The dynamic weighted and quality fusion calculation module is used to perform weighted fusion calculation on the acquired physical state data and quality weight coefficients to generate the process quality score of the current time segment, and integrate or accumulate the process quality score over the time series to obtain the real-time total quality index of the item under test. The end-side solidification and offline output module is used to solidify the calculated real-time total quality index and its corresponding process data, and output the real-time total quality index offline through a near-field communication device.

Images