A method and system for digitizing grassroots governance

Abstract

The application relates to the technical field of data processing, in particular to a method and system for digital grassroots governance, the method comprising the following steps: collecting multi-dimensional risk signals of a shop in real time, and dynamically generating a risk value corresponding to the shop based on the multi-dimensional risk signals; taking the shop with the maximum risk value as a source shop, calculating resonance strength between other shops and the source shop through industry correlation, and constructing a resonance strength network based on the resonance strength; obtaining resonance network density based on the resonance strength network; calculating intervention urgency based on the network density and the maximum risk value; and triggering an intervention signal when the intervention urgency is greater than a threshold value. The application has the characteristics of improving the timeliness of data governance to curb the risk transmission tide.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and system for digital grassroots governance. Background Technology

[0002] In the process of urban development, street shops, as an important component of the urban commercial ecosystem, are not only vital venues for residents' daily consumption but also a direct reflection of the city's economic vitality. However, current practices in the governance of street shops face many complex and urgent problems that need to be addressed.

[0003] When a single shop experiences operational difficulties, its negative impact often spreads rapidly like ripples to surrounding shops, triggering a chain reaction and creating an uncontrollable wave of risk transmission. For example, if a restaurant is exposed for hygiene problems, not only will its own customer traffic plummet, but similar restaurants and even shops in other industries nearby may also suffer from declining customer traffic and sales due to negative consumer perceptions of the area's overall commercial image. Similarly, if a shop suddenly closes due to poor management, related shops that rely on its customers, such as supporting retail stores and service businesses, may also fall into operational difficulties. This risk transmission not only affects the survival and development of individual shops but may also pose a serious threat to the stability of the entire street's commercial ecosystem.

[0004] Traditional street shop management primarily relies on manual patrols and periodic data aggregation. Manual patrols have several limitations; the subjective judgment and personal experience of patrol personnel significantly impact the accuracy and comprehensiveness of problem detection. Furthermore, due to limited manpower, the patrol area cannot cover every corner of the street, and the patrol frequency cannot be monitored in real time, easily overlooking some hidden or sudden business anomalies.

[0005] Meanwhile, the periodic data aggregation method also has obvious drawbacks. Data collection, organization, and analysis are usually carried out on a fixed schedule, such as monthly or quarterly. This leads to a serious lag in information feedback, and operational anomalies occurring during the data collection period cannot be detected and dealt with in a timely manner.

[0006] Therefore, this traditional governance model, primarily driven by experience, often intervenes only after problems have escalated and resulted in significant consequences. The decision-making mechanism suffers from severe time lag, failing to respond promptly and effectively to the complex and ever-changing situations that arise during the operation of street shops. In today's rapidly developing urban commercial environment, this outdated governance model is no longer sufficient to meet actual needs. It not only hinders the maintenance of good business order in street shops and the protection of the rights and interests of merchants and consumers, but also restricts the sustainable development of urban commerce. Summary of the Invention

[0007] To improve the timeliness of data governance and curb the spread of risks, this application provides a method and system for digital grassroots governance.

[0008] Firstly, this application provides a method for digital grassroots governance, employing the following technical solution:

[0009] A digital approach to grassroots governance includes:

[0010] Real-time collection of multi-dimensional risk signals from shops, and dynamic generation of corresponding risk values ​​for shops based on these signals;

[0011] The source shop is the shop with the highest risk value. The resonance intensity between other shops and the source shop is calculated through industry correlation. A resonance intensity network is constructed based on the resonance intensity.

[0012] Based on the resonance intensity network, the resonance network density is obtained;

[0013] Calculate the urgency of intervention based on network density and maximum risk value;

[0014] An intervention signal is triggered when the urgency of the intervention exceeds a threshold.

[0015] In one embodiment: the multidimensional risk signals include the shop's opening and closing status, compliance status, negative review rate, and customer flow data. Specifically, the step of dynamically generating the risk value corresponding to the shop based on the multidimensional risk signals includes:

[0016] Based on the store's open and closed status, obtain the ratio of the number of abnormal store openings and closings to the number of business days within a preset time period, and obtain the closure fluctuation coefficient.

[0017] Based on the compliance status and the preset compliance weights corresponding to the compliance items, the compliance deviation is calculated according to the rectification progress of the compliance items to be rectified and the preset compliance weights.

[0018] Based on passenger flow data, the degree of passenger flow anomaly is calculated by comparing the daily passenger flow with the weekly average passenger flow.

[0019] The risk value is obtained by weighting the factors of business closure fluctuation coefficient, compliance deviation, negative review rate, and abnormal customer flow.

[0020] In one embodiment, the specific steps for calculating the resonance intensity between other shops and the source shop through industry correlation include:

[0021] Based on customer flow data, obtain the number of shared customers and total customers between the two shops, and calculate the customer flow sharing rate;

[0022] Obtain the distance between two shops, and calculate the distance decay coefficient based on the distance using an exponential function.

[0023] The resonance intensity is obtained by multiplying the industry relevance, passenger flow sharing rate, and distance attenuation coefficient.

[0024] In one embodiment: the step of obtaining the resonance network density based on the resonance intensity network specifically includes:

[0025] Based on the resonant intensity network, the actual number of connections where the resonant intensity is greater than the intensity threshold is obtained;

[0026] The maximum number of connections is calculated based on the total number of valid shops on a street, where valid shops are defined as shops that are operating normally.

[0027] The resonant network density is obtained by calculating based on the actual number of connections and the maximum number of connections.

[0028] In one embodiment, the method for digital grassroots governance further includes:

[0029] Based on the resonance intensity network, the predicted risk increment of the affected shops is calculated respectively;

[0030] Update industry correlation based on predicted risk increments.

[0031] In one embodiment: the step of calculating the predicted risk increment of each affected shop based on the resonance intensity network specifically includes:

[0032] Obtain the historical problem incidence rate for affected shops;

[0033] The predicted risk increment is obtained by calculating the risk value of the source shop, the resonance intensity, and the historical problem occurrence rate.

[0034] In one embodiment: the step of obtaining the historical problem occurrence rate of affected shops specifically includes:

[0035] If a store's operating time is less than the preset time, it will be marked as a new store, and the first preset value will be used as the historical problem occurrence rate.

[0036] If the operating time of a shop is not less than the preset time, it is marked as an old shop, and the number of rectification items of the shop within the preset time, as well as the severity coefficient of the rectification items, are obtained, and the number of risk events is calculated.

[0037] Based on the number of risk events and the preset duration, the historical problem occurrence rate is calculated. Among them, the historical problem occurrence rate corresponding to old stores is greater than the second preset value.

[0038] In one embodiment: the step of updating the industry correlation based on the predicted risk increment specifically includes:

[0039] Based on the predicted risk increment and the actual risk increment of the shops on that day, the resonance intensity correction coefficient is obtained;

[0040] The industry correlation is updated based on the resonance intensity correction coefficient.

[0041] In one embodiment, the step of obtaining the resonance intensity correction coefficient based on the risk increment and the actual risk increment of the shops on that day specifically includes:

[0042] The number of shops whose risk increment exceeds a preset risk threshold is used as the predicted number of affected shops.

[0043] The number of shops whose actual risk increase on that day exceeded the preset risk threshold was obtained as the actual number of affected shops.

[0044] The resonance intensity correction coefficient is obtained based on the ratio of the actual number of affected individuals to the predicted number of affected individuals.

[0045] Secondly, this application provides a digital grassroots governance system, which adopts the following technical solution:

[0046] A digital grassroots governance system includes:

[0047] The signal acquisition module is used to collect multi-dimensional risk signals from shops in real time.

[0048] The network building module is used to construct a resonance intensity network based on resonance intensity.

[0049] The calculation module is used to dynamically generate risk values ​​corresponding to shops based on multi-dimensional risk signals; taking the shop with the highest risk value as the source shop, it calculates the resonance intensity between other shops and the source shop through industry correlation; based on the resonance intensity network, it obtains the resonance network density; based on the network density and the maximum risk value, it calculates the urgency of intervention.

[0050] The signal triggering module triggers an intervention signal when the urgency of the intervention exceeds a threshold.

[0051] In summary, this application has the following beneficial effects:

[0052] 1. By analyzing multidimensional risk signals in real time and constructing a resonance intensity network to predict risk transmission, the urgency of intervention is calculated on a daily basis to quantify the severity of the problem and thus achieve timely governance.

[0053] 2. Through risk increment analysis, the correlation between industries can be dynamically optimized, so that the prediction results can be continuously optimized according to the actual situation. Attached Figure Description

[0054] Figure 1 This is a system framework diagram of the digital grassroots governance system in this embodiment;

[0055] Figure 2 This is a flowchart of the digital grassroots governance method in this embodiment.

[0056] In the diagram, 10 is the signal acquisition module; 20 is the network construction module; 30 is the calculation module; and 40 is the signal triggering module. Detailed Implementation

[0057] The present application will be further described in detail below with reference to the accompanying drawings.

[0058] To better understand the purpose, technical solutions, and advantages of this application, it has been described and illustrated below with reference to the accompanying drawings and embodiments. However, those skilled in the art should understand that this application can be implemented without these details. In some cases, to avoid obscuring various aspects of this application due to unnecessary description, well-known methods, processes, systems, components, and / or circuits already described at a higher level will not be elaborated upon. It will be apparent to those skilled in the art that various modifications can be made to the embodiments disclosed in this application, and the general principles defined in this application can be applied to other embodiments and application scenarios without departing from the principles and scope of this application. Therefore, this application is not limited to the illustrated embodiments, but conforms to the broadest scope consistent with the scope of protection claimed in this application.

[0059] It should be noted that the descriptions of these embodiments are for the purpose of aiding understanding the present invention, but do not constitute a limitation thereof. Furthermore, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0060] In the description of this application, "several" means one or more, "more than" means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. The use of "first" and "second" in the description is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0061] In the description of this application, the terms "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples.

[0062] A digital grassroots governance system, such as Figure 1 As shown, it includes a signal acquisition module 10, a network construction module 20, a calculation module 30, and a signal triggering module 40.

[0063] The signal acquisition module 10 is used to collect multi-dimensional risk signals of shops in real time. These multi-dimensional risk signals include the shop's opening and closing status, compliance status, negative review rate, and customer flow data.

[0064] The opening and closing status of shops can be obtained through devices such as door magnetic sensors, smart meters, and cameras. Depending on the accuracy requirements and cost control, data can be obtained through a single device or a combination of multiple devices.

[0065] Compliance information is primarily obtained through a combination of government service systems and AI cameras. The government service system obtains information such as the business registration, licensing status, and law enforcement records of shops, while the AI ​​cameras are mainly used to detect in real time whether there are items obstructing the road or illegal billboards in front of shops.

[0066] Negative review rates are obtained through online platform data integration and offline complaint data aggregation. In addition, to improve accuracy, Natural Language Processing (NLP) technology is used to classify review texts, distinguishing between dimensions such as "product negative reviews," "service negative reviews," and "hygiene negative reviews," generating a visual negative review rate report.

[0067] Customer flow data is obtained through methods such as customer flow cameras and integration with store POS systems. Among these methods, integration with store POS systems is preferred. By cooperating with payment platforms, payment accounts can be hashed and encrypted. While protecting user privacy, the consumption records of the same encrypted account in different stores can be counted, thereby enabling the statistics of common customers among stores.

[0068] Network building module 20 is used to build a resonance intensity network based on resonance intensity.

[0069] The calculation module 30 is used to dynamically generate the risk value corresponding to the shop based on the multidimensional risk signal; calculate the resonance intensity between other shops and the source shop through industry correlation; take the shop with the highest risk value as the source shop, obtain the resonance network density based on the resonance intensity network; and calculate the intervention urgency based on the network density and the maximum risk value.

[0070] The signal triggering module 40 triggers an intervention signal when the urgency of intervention exceeds a threshold. After receiving the intervention signal, the execution terminal can quickly formulate a governance plan through manual or system analysis.

[0071] like Figure 2 As shown in the embodiments of this application, a method for digital grassroots governance is also provided, the steps of which include:

[0072] S100: Real-time collection of multi-dimensional risk signals from shops, and dynamic generation of corresponding risk values ​​for shops based on the multi-dimensional risk signals.

[0073] In this step, multidimensional risk signals include the store's opening and closing status, compliance status, negative review rate, and customer traffic data.

[0074] As an example, the method for dynamically generating risk values ​​for shops based on multidimensional risk signals may include:

[0075] Based on the store's open and closed status, obtain the ratio of the number of abnormal store openings and closings to the number of business days within a preset time period, and obtain the closure fluctuation coefficient.

[0076] Based on the compliance status and the preset compliance weights corresponding to the compliance items, the compliance deviation is calculated according to the rectification progress of the compliance items to be rectified and the preset compliance weights.

[0077] Based on passenger flow data, the degree of passenger flow anomaly is calculated by comparing the daily passenger flow with the weekly average passenger flow.

[0078] The risk value is obtained by weighting the factors of business closure fluctuation coefficient, compliance deviation, negative review rate, and abnormal customer flow.

[0079] In this embodiment, the business closure fluctuation coefficient = number of abnormal store openings and closings / number of business days, and the preset time is usually set on a weekly or monthly basis. This can improve the sensitivity of fluctuation detection and provide faster and more timely feedback on store operation issues.

[0080] In this embodiment, compliance deviation = Σ(preset compliance weight of items requiring rectification) × (1 - rectification progress), and rectification progress = min(1, actual rectification items / items requiring rectification). A preset compliance weight is pre-set for each compliance item. When setting this weight, the higher the risk of transmission, the larger the preset compliance weight. For example, the weight of safety issues is greater than that of hygiene issues, and the weight of hygiene issues is greater than that of road obstruction issues.

[0081] In another embodiment, a time penalty mechanism can be introduced for the rectification progress, namely, compliance deviation = Σ(preset compliance weight of the rectification item) × (1 - rectification progress) × time penalty coefficient, and time penalty coefficient = e^(-δ·preset rectification cycle / actual rectification time). Thus, the shorter the actual rectification time, the smaller the corresponding time penalty coefficient.

[0082] In this embodiment, the passenger flow anomaly degree = |Daily passenger flow - Weekly average passenger flow| / Weekly average passenger flow, and passenger flow that is higher or lower than the average level is considered an abnormal situation.

[0083] In this embodiment, the risk value is calculated as follows: (Business interruption fluctuation coefficient × w1) + (Compliance deviation × w2) + (Negative review rate × w3) + (Customer flow anomaly degree × w4). The weights w1, w2, w3, and w4 are all preset values, and w1 + w2 + w3 + w4 = 1.

[0084] S200: Taking the shop with the highest risk value as the source shop, calculate the resonance intensity between other shops and the source shop through industry correlation, and construct a resonance intensity network based on the resonance intensity.

[0085] The main purpose is to intervene in a timely manner, because under normal circumstances, the shops with the highest risk values ​​can reflect the general or prominent problems of the street. Therefore, it is sufficient to conduct testing and intervention on the shops with the highest risk values.

[0086] By calculating the resonance intensity between shops, we can understand the resonance between the source shop and other shops on the street. The greater the resonance intensity, the more easily it is affected. In this way, we can directly construct a resonance intensity network, thereby more intuitively observing the risk diffusion.

[0087] As an example, the method for calculating the resonance intensity between other shops and the source shop through industry correlation specifically includes the following steps:

[0088] Based on customer flow data, obtain the number of shared customers and total customers between the two shops, and calculate the customer flow sharing rate;

[0089] Obtain the distance between two shops, and calculate the distance decay coefficient based on the distance using an exponential function.

[0090] The resonance intensity is obtained by multiplying the industry relevance, passenger flow sharing rate, and distance attenuation coefficient.

[0091] In this embodiment, the customer flow sharing rate = number of common customers / total number of customers. Taking stores A and B as examples, the number of customers of A on the same day is A1, and the number of customers of B on the same day is B1. The number of common customers of stores A and B is A∩B, and the total number of customers is A1+B1-A∩B.

[0092] The industry relevance is a preset value, such as same industry = 1.0, complementary industry = 0.8 (e.g., catering-milk tea), unrelated industry = 0.3, etc.

[0093] In this embodiment, resonance intensity = industry correlation × customer flow sharing rate × distance attenuation coefficient, and distance attenuation coefficient = e^(-distance / 50). In this embodiment, 50 meters is used as the dividing point of influence. That is, when the distance between two stores reaches 50 meters, the risk transmission intensity attenuates to 36.8%. This data is formed by fitting the survey data of commercial streets in multiple cities. According to the survey results, when the distance between two stores reaches 50-80 meters, the cross-store consumption ratio is less than 40%.

[0094] S300: Based on the resonance intensity network, obtain the resonance network density.

[0095] In this step, the resonant network density is mainly used to predict the activity and density of risk diffusion. The larger the value, the greater the diffusion risk and the wider the impact range.

[0096] As an example, the steps for obtaining the resonance network density based on the resonance intensity network specifically include:

[0097] Based on the resonant intensity network, the actual number of connections where the resonant intensity is greater than the intensity threshold is obtained;

[0098] The maximum number of connections is calculated based on the total number of valid shops on a street, where valid shops are defined as shops that are operating normally.

[0099] The resonant network density is obtained by calculating based on the actual number of connections and the maximum number of connections.

[0100] In this embodiment, the resonant network density = actual number of connections / maximum number of connections.

[0101] Where, the actual number of connections = ∑_{i=1}^{n}∑_{j>i}^{n}[res_{ij}>ρ], where ∑_{i=1}^{n} represents traversing from the first shop, ∑_{j>i}^{n} represents checking only the shops that come after the first one, and res_{ij} is the resonance intensity between shops i and j. Iverson brackets (1 if the condition is true, 0 otherwise), i.e., [res_{ij}>ρ] means that the judgment condition is that when the resonance intensity between two shops exceeds the intensity threshold ρ, it is counted as a valid connection, and the number of valid connections is finally calculated as the actual number of connections.

[0102] The maximum number of connections is n(n-1) / 2, where n represents the total number of valid shops on the street. The definition of the total number of valid shops can be set freely. It can be the total number of non-vacant shops or the total number of shops that are open for business on the day.

[0103] S400 calculates the urgency of intervention based on network density and maximum risk value.

[0104] In the above steps, the intervention urgency = maximum risk value × resonance network density.

[0105] S500: When the urgency of intervention exceeds the threshold, an intervention signal is triggered.

[0106] In another embodiment, the method for digital grassroots governance further includes:

[0107] S600, based on the resonance intensity network, calculates the predicted risk increment of affected shops respectively.

[0108] S700 updates industry correlation based on predicted risk increments.

[0109] As an example, the method for calculating the predicted risk increment of affected shops based on the resonance intensity network specifically includes the following steps:

[0110] Obtain the historical problem incidence rate for affected shops;

[0111] The predicted risk increment is obtained by calculating the risk value of the source shop, the resonance intensity, and the historical problem occurrence rate.

[0112] In this embodiment, the predicted risk increment = source shop risk value × resonance intensity × historical problem occurrence rate, and the risk transmission equation constructed above is used to effectively predict the transmitted risk.

[0113] As an example, the steps for obtaining the historical problem occurrence rate of affected shops specifically include:

[0114] If a store's operating time is less than the preset time, it will be marked as a new store, and the first preset value will be used as the historical problem occurrence rate.

[0115] If the operating time of a shop is not less than the preset time, it is marked as an old shop, and the number of rectification items of the shop within the preset time, as well as the severity coefficient of the rectification items, are obtained, and the number of risk events is calculated.

[0116] Based on the number of risk events and the preset duration, the historical problem occurrence rate is calculated. Among them, the historical problem occurrence rate corresponding to old stores is greater than the second preset value.

[0117] In this embodiment, the store is identified as a new store or an old store by comparing the store's operating time with the preset time. Since new stores lack operating data, the first preset value is directly used as the historical problem occurrence rate.

[0118] Established stores, on the other hand, conduct statistical calculations based on the rectification items. Specifically, the historical problem occurrence rate = number of risk events within a preset time period / preset time period, where the number of risk events = Σ(compliant items requiring rectification × problem type weight). The number of risk events is not set directly as a simple number, but is calculated in conjunction with the problem type weight. This allows for differentiation of the severity of each compliant item requiring rectification, thus providing a more accurate reflection of the historical problem occurrence rate.

[0119] As an example, the method for updating industry correlation based on predicted risk increments specifically includes the following steps:

[0120] Based on the predicted risk increment and the actual risk increment of the shops on that day, the resonance intensity correction coefficient is obtained;

[0121] The industry correlation is updated based on the resonance intensity correction coefficient.

[0122] In this embodiment, the new industry correlation degree = industry correlation degree × resonance intensity correction coefficient.

[0123] In addition, the steps to obtain the resonance intensity correction coefficient based on the risk increment and the actual risk increment of the shops on that day specifically include:

[0124] The number of shops whose risk increment exceeds a preset risk threshold is used as the predicted number of affected shops.

[0125] The number of shops whose actual risk increase on that day exceeded the preset risk threshold was obtained as the actual number of affected shops.

[0126] The resonance intensity correction coefficient is obtained based on the ratio of the actual number of affected individuals to the predicted number of affected individuals.

[0127] In this embodiment, the resonance intensity correction coefficient = actual conduction intensity / predicted conduction intensity. It is obtained by statistically analyzing stores that exceed the preset risk threshold through a preset risk threshold, thereby obtaining the actual conduction intensity and the predicted conduction intensity, that is, the predicted number of affected stores and the actual number of affected stores. The correction coefficient is obtained by comparing the actual and predicted conduction intensities.

[0128] In this process, risks do not always originate from the source shop; they can also spread to other shops affected by it. For example, if shop A is the source shop, shop B is directly affected by shop A, and shop C is not directly affected by shop A but is directly affected by shop B, then the risk will propagate from shop A to shop B, and then from shop B to shop C. In this case, the risk cannot be directly observed on the resonance intensity network. Therefore, a resonance intensity correction coefficient is used to correct the industry correlation.

[0129] The embodiments described in this specific implementation are preferred embodiments of this application and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A method of digitizing grassroots governance, characterized in that, include: Real-time collection of multi-dimensional risk signals from shops, and dynamic generation of corresponding risk values ​​for shops based on these signals; The source shop is the shop with the highest risk value. The resonance intensity between other shops and the source shop is calculated through industry correlation. A resonance intensity network is constructed based on the resonance intensity. Based on the resonance intensity network, the resonance network density is obtained; Calculate the urgency of intervention based on network density and maximum risk value; When the urgency of the intervention exceeds a threshold, an intervention signal is triggered; Based on the resonance intensity network, the predicted risk increment of the affected shops is calculated respectively; Update industry correlation based on predicted risk increments; Specifically, the step of obtaining the resonance network density based on the resonance intensity network includes: Based on the resonant intensity network, the actual number of connections where the resonant intensity is greater than the intensity threshold is obtained; The maximum number of connections is calculated based on the total number of valid shops on a street, where valid shops are defined as shops that are operating normally. The resonant network density is obtained by calculating based on the actual number of connections and the maximum number of connections.

2. The method of digitizing grass-roots governance as claimed in claim 1, wherein: The multidimensional risk signals include the shop's opening and closing status, compliance status, negative review rate, and customer traffic data. Specifically, the step of dynamically generating the risk value corresponding to the shop based on the multidimensional risk signals includes: Based on the store's open and closed status, obtain the ratio of the number of abnormal store openings and closings to the number of business days within a preset time period, and obtain the closure fluctuation coefficient. Based on the compliance status and the preset compliance weights corresponding to the compliance items, the compliance deviation is calculated according to the rectification progress of the compliance items to be rectified and the preset compliance weights. Based on passenger flow data, the degree of passenger flow anomaly is calculated by comparing the daily passenger flow with the weekly average passenger flow. The risk value is obtained by weighting the factors of business closure fluctuation coefficient, compliance deviation, negative review rate, and abnormal customer flow.

3. The method of digitizing grass-roots governance as claimed in claim 2, wherein, The specific steps for calculating the resonance intensity between other shops and the source shop through industry correlation include: Based on customer flow data, obtain the number of shared customers and total customers between the two shops, and calculate the customer flow sharing rate; Obtain the distance between two shops, and calculate the distance decay coefficient based on the distance using an exponential function. The resonance intensity is obtained by multiplying the industry relevance, passenger flow sharing rate, and distance attenuation coefficient.

4. The method of digitizing grass-roots governance as claimed in claim 1, wherein, The steps for calculating the predicted risk increment of affected shops based on the resonance intensity network specifically include: Obtain the historical problem incidence rate for affected shops; The predicted risk increment is obtained by calculating the risk value of the source shop, the resonance intensity, and the historical problem occurrence rate.

5. A method of digitizing grass-roots governance as claimed in claim 4, wherein, The steps for obtaining the historical problem incidence rate of affected shops specifically include: If a store's operating time is less than the preset time, it will be marked as a new store, and the first preset value will be used as the historical problem occurrence rate. If the operating time of a shop is not less than the preset time, it is marked as an old shop, and the number of rectification items of the shop within the preset time, as well as the severity coefficient of the rectification items, are obtained, and the number of risk events is calculated. Based on the number of risk events and the preset duration, the historical problem occurrence rate is calculated. Among them, the historical problem occurrence rate corresponding to old stores is greater than the second preset value.

6. The method of digitizing grass-roots governance as claimed in claim 1, wherein, The steps for updating industry correlation based on predicted risk increments specifically include: Based on the predicted risk increment and the actual risk increment of the shops on that day, the resonance intensity correction coefficient is obtained; The industry correlation is updated based on the resonance intensity correction coefficient.

7. A method of digitizing grass-roots governance as claimed in claim 6, wherein, The steps for obtaining the resonance intensity correction coefficient based on the risk increment and the actual risk increment of the shops on that day specifically include: The number of shops whose risk increment exceeds a preset risk threshold is used as the predicted number of affected shops. The number of shops whose actual risk increase on that day exceeded the preset risk threshold was obtained as the actual number of affected shops. The resonance intensity correction coefficient is obtained based on the ratio of the actual number of affected individuals to the predicted number of affected individuals.

8. A system for digitizing grass-roots governance, the method for digitizing grass-roots governance as claimed in any one of claims 1-7 being applied, characterized in that, include: The signal acquisition module (10) is used to collect multi-dimensional risk signals of shops in real time; Network building module (20) is used to build a resonance intensity network based on resonance intensity; The calculation module (30) is used to dynamically generate the risk value corresponding to the shop based on the multidimensional risk signal; The resonance strength between other shops and the source shop is calculated by industry correlation; the source shop is selected as the shop with the highest risk value, and the resonance network density is obtained based on the resonance strength network. Calculate the urgency of intervention based on network density and maximum risk value; The signal triggering module (40) triggers an intervention signal when the urgency of the intervention is greater than a threshold.

Images