A method for applying data elements in the field of urban governance

Abstract

The present disclosure is about an application method of data elements in the field of urban governance, and relates to the field of big data processing technology. The method includes: parsing target data resources to obtain target social demographic data, target area attribute data, and target area economic data of the target area; inputting the target social demographic data, target area attribute data, target area economic data, and the configured position of the target object into a preset object position prediction model to obtain an object position prediction result; scoring the object position prediction result based on a preset object position recommendation model to obtain a first scoring result, and determining the target object to be configured position from the object position prediction result according to the first scoring result; uploading the target object to be configured position to the blockchain, so that the operation and maintenance personnel obtain the target object to be configured position from the blockchain and perform object configuration. The present disclosure improves the utilization rate of data resources.

Description

Technical Field

[0001] The disclosed embodiments relate to the field of big data processing technology, and more specifically, to an application method based on data elements in the field of urban governance. Background Art

[0002] At present, the data work system has taken shape, the coordinated digital development efforts have been steadily strengthened, the construction of data infrastructure has been vigorously promoted, and open cooperation in the data field has been further expanded, and data work has made a good start. At this stage, one of the key tasks of data processing is to continuously improve the data basic system, give full play to the basic resource role and innovation engine role of data, and continuously strengthen, optimize and expand the digital economy, so as to provide strong support for building a new development pattern, building a modern economic system, and building new competitive advantages. Therefore, promoting data assetization and opening up the path from assets to capital for data elements is an urgent problem to be solved.

[0003] The main concept of existing data processing solutions is to directly assetize data resources; however, this method has the following defects: on the one hand, data resources are not applied to the field of urban governance, which leads to the problem of waste of data resources; on the other hand, when data resources are used, it is impossible to track the users of data resources, which makes the security of data resources low.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the present disclosure is to provide a method for applying data elements in the field of urban governance, thereby overcoming, at least to a certain extent, the problem of data resource waste and the problem of low security of data resources caused by the limitations and defects of related technologies.

[0006] According to one aspect of the present disclosure, a method for applying data elements in the field of urban governance is provided, including:

[0007] Obtaining target data resources of the target area from the blockchain network, and parsing the target data resources to obtain target social demographic data, target area attribute data, and target area economic data of the target area;

[0008] Obtaining the configured position of the target object in the target area, and inputting the target socio-demographic data, the target area attribute data, the target area economic data and the configured position of the target object into a preset object position prediction model to obtain an object position prediction result;

[0009] Scoring the object position prediction result based on a preset object position recommendation model to obtain a first scoring result, and determining the target object to-be-configured position from the object position prediction result according to the first scoring result;

[0010] The location of the target object to be configured is uploaded to the blockchain, so that the operation and maintenance personnel can obtain the location of the target object to be configured from the blockchain and perform object configuration.

[0011] In an exemplary embodiment of the present disclosure, the preset object position prediction model includes an embedding mapping layer, a coding layer, and a hybrid expert model layer;

[0012] The target socio-demographic data, target area attribute data, target area economic data and the configured location of the target object are input into a preset object location prediction model to obtain an object location prediction result, including:

[0013] Generate the regional basic information to be predicted based on the target social demographic data, target regional attribute data and target regional economic data, and generate the contextual information to be predicted based on the configured location of the target object and the preset model prompt parameters;

[0014] Performing word embedding processing on the region basic information to be predicted based on the embedding mapping layer to obtain a first region feature, and performing embedding mapping processing on the context information to be predicted based on the embedding mapping layer to obtain a context marker sequence;

[0015] The first region feature and the context marker sequence are encoded based on the encoding layer to obtain a context overall representation, and the context marker sequence and the context overall representation are predicted based on the hybrid expert model layer to obtain the object position prediction result.

[0016] In an exemplary embodiment of the present disclosure, the hybrid expert model layer includes a gated network model and an expert neural network model;

[0017] The process of predicting the context marker sequence and the overall context representation based on the hybrid expert model layer to obtain the object position prediction result includes:

[0018] Determining a model weight of the expert neural network model based on the gating network model according to the contextual marker sequence, and determining a target neural network model required to perform an object position prediction task from the expert neural network according to the model weight;

[0019] The context marker sequence and the overall context representation are input into the target neural network model to obtain the object position prediction result.

[0020] In an exemplary embodiment of the present disclosure, the gated network model includes a first gated network model and a second gated network model;

[0021] Wherein, determining the model weight of the expert neural network model according to the contextual marker sequence based on the gated network model, and determining the target neural network model required to perform the object position prediction task from the expert neural network according to the model weight, includes:

[0022] Determine a first model weight of the expert neural network model in the object configuration density dimension based on the first gating network model according to the contextual flag sequence, and determine a first target neural network model required to perform the object position prediction task in the object configuration density dimension from the expert neural network according to the first model weight;

[0023] Based on the second gating network model, according to the context flag sequence, the second model weight of the expert neural network model in the object configuration breadth dimension is determined, and according to the second model weight, the second target neural network model required to perform the object position prediction task in the object configuration breadth dimension is determined from the expert neural network.

[0024] In an exemplary embodiment of the present disclosure, the context marker sequence and the overall context representation are input into the target neural network model to obtain the object position prediction result, including:

[0025] Inputting the contextual marker sequence and the overall context representation into the first target neural network model to obtain a first prediction result on the object configuration dimension;

[0026] Inputting the contextual marker sequence and the overall context representation into the second target neural network model to obtain a second prediction result in the dimension of object configuration breadth;

[0027] Configure a first dimension weight value for a first prediction result in the object configuration density dimension, and configure a second dimension weight value for a second prediction result in the object configuration breadth dimension;

[0028] The first dimension weight value and the first prediction result, the second dimension weight value and the second prediction result are weightedly summed to obtain the object position prediction result.

[0029] In an exemplary embodiment of the present disclosure, scoring the object position prediction result based on a preset object position recommendation model to obtain a first scoring result includes:

[0030] Calculate the linear regression part of the object position prediction result based on the internal nodes of the preset object position recommendation model;

[0031] The linear regression part is normalized based on the normalization layer where the leaf node of the preset object position recommendation model is located to obtain the first scoring result.

[0032] In an exemplary embodiment of the present disclosure, the preset object position prediction model is obtained in the following manner:

[0033] Acquire current social demographic data, current regional attribute data and current regional economic data of the object configured area, and determine a first object configuration position of the object configured area before the object position is adjusted and a second object configuration position of the object configured area after the object position is adjusted;

[0034] Inputting the current social demographic data, the current regional attribute data, the current regional economic data and the first object configuration position into the large model to be trained, and obtaining a first prediction result in the object configuration density dimension and a second prediction result in the object configuration breadth dimension;

[0035] Constructing a first loss function according to a second configuration density in the second object configuration position and the first prediction result, and constructing a second loss function according to a second configuration breadth in the second object configuration position and the second prediction result;

[0036] A target loss function is constructed based on the first loss function and the second loss function, and the parameters in the large model to be trained are adjusted based on the target loss function to obtain the preset object position prediction model.

[0037] According to one aspect of the present disclosure, there is provided a device for applying data elements in the field of urban governance, including:

[0038] A data resource parsing module, used to obtain target data resources of a target area from a blockchain network, and parse the target data resources to obtain target social demographic data, target area attribute data, and target area economic data of the target area;

[0039] A location prediction result determination module is used to obtain the configured location of the target object in the target area, and input the target socio-demographic data, target area attribute data, target area economic data and the configured location of the target object into a preset object location prediction model to obtain an object location prediction result;

[0040] a module for determining a position to be configured, configured to score the object position prediction result based on a preset object position recommendation model to obtain a first scoring result, and determine the target object position to be configured from the object position prediction result according to the first scoring result;

[0041] The module for uploading the position to be configured is used to upload the position to be configured of the target object to the blockchain, so that the operation and maintenance personnel can obtain the position to be configured of the target object from the blockchain and perform object configuration.

[0042] According to one aspect of the present disclosure, there is provided a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the computer program implements the application method of any one of the above-mentioned data elements in the field of urban governance.

[0043] According to one aspect of the present disclosure, there is provided an electronic device, including:

[0044] Processor; and

[0045] A memory, configured to store executable instructions of the processor;

[0046] Among them, the processor is configured to execute the application method of the data elements described in any one of the above in the field of urban governance by executing the executable instructions.

[0047] The present disclosure provides a method for applying data elements in the field of urban governance, which obtains target data resources of a target area from a blockchain network and parses the target data resources to obtain target socio-demographic data, target area attribute data, and target area economic data of the target area; then obtains the configured position of a target object in the target area, and inputs the target socio-demographic data, target area attribute data, target area economic data, and the configured position of the target object into a preset object position prediction model to obtain an object position prediction result; then scores the object position prediction result based on the preset object position recommendation model to obtain a first scoring result, and determines the target from the object position prediction result according to the first scoring result. The target object is located at the position to be configured; finally, the target object is located at the position to be configured to the blockchain, so that the operation and maintenance personnel can obtain the target object from the blockchain and perform object configuration, thereby realizing the application of data resources in the field of urban governance, solving the problem of waste of data resources in the prior art due to the failure to apply data resources to the field of urban governance, and improving the utilization rate of target data resources; on the other hand, since the corresponding data resources can be obtained from the blockchain network and the target object is located at the position to be configured to the blockchain, the problem of low security of data resources due to the inability to track the users of data resources when they are used in the prior art is solved, thereby improving the security of data resources.

[0048] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0050] Figure 1 A flowchart schematically illustrates a method for applying data elements in the field of urban governance according to an example embodiment of the present disclosure.

[0051] Figure 2 A diagram schematically shows an example structure of an application system of data elements in the field of urban governance according to an example embodiment of the present disclosure.

[0052] Figure 3 A schematic diagram shows an example structure of a preset object position prediction model according to an example embodiment of the present disclosure.

[0053] Figure 4 A diagram schematically illustrates an example structure of a hybrid expert model layer in a preset object position prediction model according to an example embodiment of the present disclosure.

[0054] Figure 5 A method flow chart schematically illustrates a training process of a preset object position prediction model according to an example embodiment of the present disclosure.

[0055] Figure 6 A schematic diagram shows an example structure of a preset object location recommendation model according to an example embodiment of the present disclosure.

[0056] Figure 7 A flowchart schematically illustrates a method for determining a prediction result of an object position according to an exemplary embodiment of the present disclosure.

[0057] Figure 8 A block diagram schematically illustrates an application device of data elements in the field of urban governance according to an example embodiment of the present disclosure.

[0058] Fig. 9 An electronic device for implementing a method for applying data elements in the field of urban governance according to an example embodiment of the present disclosure is schematically illustrated.

[0059] Fig.10A computer-readable storage medium for storing an application method of data elements in the field of urban governance according to an example embodiment of the present disclosure is schematically illustrated. DETAILED DESCRIPTION

[0060] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted; in other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0061] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0062] This exemplary embodiment first provides a method for applying data elements in the field of urban governance. The method can be run on a server, server cluster or cloud server, etc. Of course, those skilled in the art can also run the method disclosed in this disclosure on other platforms as required, and this exemplary embodiment does not specifically limit this. Figure 1 As shown, the application method of this data element in the field of urban governance may include the following steps:

[0063] Step S110. Obtain target data resources of the target area from the blockchain network, and parse the target data resources to obtain target social demographic data, target area attribute data, and target area economic data of the target area;

[0064] Step S120. Obtain the configured position of the target object in the target area, and input the target socio-demographic data, target area attribute data, target area economic data and the configured position of the target object into a preset object position prediction model to obtain an object position prediction result;

[0065] Step S130. Scoring the object position prediction result based on a preset object position recommendation model to obtain a first scoring result, and determining the target object to be configured position from the object position prediction result according to the first scoring result;

[0066] Step S140. Upload the target object's location to be configured to the blockchain, so that the operation and maintenance personnel can obtain the target object's location to be configured from the blockchain and perform object configuration.

[0067] In the application method of the above data elements in the field of urban governance, the target data resources of the target area are obtained from the blockchain network, and the target data resources are parsed to obtain the target socio-demographic data, target area attribute data and target area economic data of the target area; then the configured position of the target object in the target area is obtained, and the target socio-demographic data, target area attribute data, target area economic data and the configured position of the target object are input into a preset object position prediction model to obtain an object position prediction result; then the object position prediction result is scored based on the preset object position recommendation model to obtain a first scoring result, and the target object to be determined from the object position prediction result according to the first scoring result. configuration location; finally, the target object's to-be-configured location is uploaded to the blockchain, so that the operation and maintenance personnel can obtain the target object's to-be-configured location from the blockchain and perform object configuration, thereby realizing the application of data resources in the field of urban governance, solving the problem of waste of data resources in the prior art due to the failure to apply data resources to the field of urban governance, and improving the utilization rate of target data resources; on the other hand, since the corresponding data resources can be obtained from the blockchain network and the target object's to-be-configured location is uploaded to the blockchain, the problem of low security of data resources in the prior art due to the inability to track the users of data resources when they are used is solved, thereby improving the security of data resources.

[0068] Hereinafter, the application method of the data elements recorded in the exemplary embodiment of the present disclosure in the field of urban governance will be explained and illustrated in detail with reference to the accompanying drawings.

[0069] First, the technical implementation principle of the example embodiment of the present disclosure is explained and illustrated. Specifically, the application method of the data elements recorded in the example embodiment of the present disclosure in the field of urban governance is mainly for the purpose of applying the data elements in the object detection configuration in the smart property scenario; wherein, the objects in the smart property scenario recorded here may include but are not limited to street lights, green plants, trash cans, leisure areas, roadblocks and parking lots, etc., and may also include other objects; that is, the objects in the target area can be optimized based on the various data in the target area; for example, sparse processing is performed on overly dense areas, and some areas that do not require object configuration are cancelled, etc. Based on the application method of the data elements in the field of urban governance recorded in the example embodiment of the present disclosure, on the basis of improving the utilization rate of data resources, it is possible to further achieve the purpose of studying and understanding the ideas of data resource governance, supporting local officials and getting close to the lives of the people.

[0070] First, the application system of the data elements involved in the exemplary embodiment of the present disclosure in the field of urban governance is explained and illustrated. Figure 2 As shown, the application of the data elements in the field of urban governance may include a customer service system 210, a global data element assetization intelligent service platform 220 and an integrated data base 230; wherein the customer service system, the global data element assetization intelligent service platform and the integrated data base may be communicatively connected via a high-speed data bus.

[0071] In the process of actual application, the integrated data base 230, as the cornerstone of the entire project, integrates the data of various systems within the enterprise and organization, and realizes the unified storage and management of data; that is, the original resource data can be obtained and stored through the integrated data base; further, through the integrated data base, the problem of data islands has been fundamentally solved, and data can be circulated and shared more smoothly; in addition, the integrated data base also uses advanced data governance methods to clean, integrate and standardize data to ensure the accuracy and consistency of data, provide basic data integration and governance capabilities for data transactions, make data value measurable, and meet data transaction standards.

[0072] Secondly, the global data element asset intelligent management service platform is based on an integrated data base, using advanced artificial intelligence and big data technologies to deeply mine and utilize data assets; this platform provides data trading and data sharing functions, such as data asset evaluation, title registration, review pricing and trading services, as well as data product development for data resource governance, etc. Under this premise, enterprises and organizations can have a clearer understanding of their data asset status, discover the potential value in the data, and formulate more accurate business strategies accordingly; at the same time, through this platform, enterprises and organizations can trade or share their data assets, thereby achieving optimal allocation of data resources and mutual benefit and win-win results; based on this, it will not only help promote the prosperity and development of the data market, but also promote cooperation and exchanges between enterprises and organizations, and jointly promote the progress of the entire industry. The application method of data elements in the field of urban governance recorded in the example embodiment of this disclosure can be realized based on the target data resources obtained from the integrated data base.

[0073] Furthermore, the customer service system described above can be used to display the data directory of standard resource data, and can also be used to display the functions of the system, so that users can select corresponding data resources according to actual needs, thereby realizing the assetization of data resources.

[0074] The following will explain and illustrate the preset object position prediction model described in the exemplary embodiment of the present disclosure. Figure 3 As shown, the preset object position prediction model may include a first input layer 310, an embedding mapping layer 320, a coding layer 330, a hybrid expert model layer 340 and a first output layer 350; at the same time, referring to Figure 4 As shown, the hybrid expert model layer recorded here may include a gated network model and an expert neural network model; the gated network model recorded here may include a first gated network model and a second gated network model; further, the specific operations required to be performed at each model level will be described in detail later, and no further details will be given here. Furthermore, the encoding layer 330 recorded here may be a multi-layer bidirectional Transformer or a deep interest network (DIN). In the actual application process, it can be determined according to actual needs, and this example does not impose any special restrictions on this; and the hybrid expert model layer recorded here may be implemented based on Expert or on a factor decomposition machine (FM). In the actual application process, it may be determined according to actual needs, and this example does not impose any special restrictions on this.

[0075] The following will be combined Figure 5Explain and illustrate the specific training process of the preset object position prediction model. For details, refer to Figure 5 As shown, the specific training process of the preset object position prediction model may include the following steps:

[0076] Step S510, obtaining current social demographic data, current regional attribute data and current regional economic data of the object configured area, and determining a first object configuration position of the object configured area before the object position is adjusted and a second object configuration position of the object configured area after the object position is adjusted;

[0077] Step S520, inputting the current social demographic data, the current regional attribute data, the current regional economic data and the first object configuration position into the large model to be trained, and obtaining a first prediction result in the object configuration density dimension and a second prediction result in the object configuration breadth dimension;

[0078] Step S530, constructing a first loss function according to a second configuration density in the second object configuration position and the first prediction result, and constructing a second loss function according to a second configuration breadth in the second object configuration position and the second prediction result;

[0079] Step S540, constructing a target loss function based on the first loss function and the second loss function, and adjusting the parameters in the large model to be trained based on the target loss function to obtain the preset object position prediction model.

[0080] Hereinafter, step S510 to step S540 will be explained and illustrated. Specifically, the object configured area recorded here refers to an area where the configuration density and configuration breadth of the object have been adjusted to achieve a comprehensive consideration of two dimensions, namely, resource waste and user experience; the current social demographic data recorded here may include age data, family data, employment data, workplace data, school data, and commuting data, etc., of the area; wherein age data may be, for example, age structure (infants, children, teenagers, youth, middle-aged, and elderly), family data may be, for example, family size (the number of people in a family), employment data may be, for example, employment rate (the proportion of employed people in the total population), workplace data may be, for example, work group distribution (the distribution of the number of people in each industry), school data may be, for example, school size distribution (the number of people in a school), commuting data may be, for example, specific commuting duration and commuting time, etc.; the current regional attribute data recorded here may include a regional map, geographical location, climate characteristics, etc. of the area, and the current regional economic data recorded here may include various economic data of the area in a specific time period, which may be selected according to actual needs in the actual application process, and this example does not impose any special restrictions on this.

[0081] Furthermore, after obtaining the corresponding data, it is necessary to preprocess the current social demographic data, the current regional attribute data, and the current regional economic data; the specific preprocessing process is as follows: first, for discrete features, One-Hot encoding can be performed directly; second, for continuous features, bucketing can be performed (nine bucket boundaries are defined according to the 10th, 20th, 30th, ..., 90th percentiles of the feature of all users sorted from small to large), and then the bucket number is One-Hot encoded; then, after encoding, it can be input into the model to obtain the corresponding prediction results. Finally, after obtaining the prediction results, a loss function can be constructed to adjust the parameters. The constructed loss function can refer to the following formulas (1) to (3):

[0082] ; Formula (1)

[0083] ; Formula (2)

[0084] ; Formula (3)

[0085] in, is the target loss function, is the first loss function, is the second loss function, N is the total number of objects corresponding to the second object configuration position; is the first prediction result, is the second prediction result, is the process of determining the first prediction result, is the process of determining the second prediction result; m and n represent the weight values ​​of the configuration density dimension and the object configuration breadth dimension; in the actual application process, m and n can be selected according to actual needs, and this example does not impose any special restrictions on this; is the loss function constructed by the second configuration density and the first prediction result, is a loss function constructed by the second configuration breadth and the second prediction result; is the second configuration density, is the second configuration width; i represents the i-th object.

[0086] The following will explain and illustrate the preset object location recommendation model. Figure 6 As shown, the preset object location recommendation model may include multiple internal nodes and multiple leaf nodes; wherein the internal nodes may be used to calculate the linear regression part, and the leaf nodes may be used to calculate the specific scoring results.

[0087] The following will be combined Figure 2-Figure 6 right Figure 1 The application methods of the data elements shown in the data in the field of urban governance are further explained and illustrated. Specifically:

[0088] In step S110, the target data resources of the target area are obtained from the blockchain network, and the target data resources are parsed to obtain the target socio-demographic data, target area attribute data and target area economic data of the target area.

[0089] In this example embodiment, first, it is necessary to obtain the target data resources of the target area from the blockchain network; wherein, the target area recorded here may be a specific urban area or a county-level area or a village area, etc., and this example does not specifically limit this; the target data resources recorded here are obtained by integrating all the data resources included in the target area; at the same time, the reason why it is necessary to obtain the target data resources from the blockchain network is to ensure that the target data resources cannot be tampered with on the basis of ensuring the security of the target data resources; at the same time, the specific usage of the target data resources can also be tracked in a timely manner.

[0090] Secondly, the target data resources are parsed to obtain the target socio-demographic data, target area attribute data and target area economic data of the target area; wherein the target socio-demographic data recorded here may be basic socio-demographic indicators, which may include age data, family data, employment data, workplace data, school data and commuting data of the target area, etc.; wherein the age data may be, for example, age structure (infants, children, teenagers, youth, middle-aged, elderly), the family data may be, for example, family size (the number of people in the family), the employment data may be, for example, employment rate (the proportion of employed people in the total population), the workplace data may be, for example, work group distribution (the number of people in each industry), the school data may be, for example, school size distribution (the number of people in the school), the commuting data may be, for example, specific commuting duration and commuting time, etc.; the target area attribute data recorded here may include the regional map, geographical location, climate characteristics, etc. of the target area, and the target area economic data recorded here may include various economic data of the target area in a specific time period, which may be selected according to actual needs in the actual application process, and this example does not impose any special restrictions on this.

[0091] In step S120, the configured position of the target object in the target area is obtained, and the target socio-demographic data, target area attribute data, target area economic data and the configured position of the target object are input into a preset object position prediction model to obtain an object position prediction result.

[0092] In this example embodiment, first, the configured position of the target object in the target area is obtained; wherein the configured position of the target object recorded here refers to the position of the object that has been configured in the area and the distance between each object configuration position, etc.; secondly, the object position prediction result is determined; specifically, refer to Figure 7 As shown, the specific process of determining the object position prediction result may include the following steps:

[0093] Step S710, generating the regional basic information to be predicted according to the target socio-demographic data, target regional attribute data and target regional economic data, and generating the contextual information to be predicted according to the configured position of the target object and the preset model prompt parameters.

[0094] Specifically, in the actual application process, first, data preprocessing is performed on the target social demographic data, target regional attribute data, target regional economic data and the configured location of the target object; wherein, the specific data preprocessing process is: on the one hand, for discrete features, One-Hot encoding can be performed directly; on the other hand, for continuous features, bucketing can be performed (nine bucket boundaries are defined according to the 10th, 20th, 30th, ..., 90th percentiles of the feature of all users sorted from small to large), and then the bucket labels to which they belong are One-Hot encoded; wherein, the discrete features recorded here may include but are not limited to enumerable features, such as gender, occupation, specific regional coordinate position, etc.; the continuous features recorded here may include but are not limited to numerical continuous features, and may include but are not limited to age, income, etc.; the preset model prompt parameters recorded here refer to the Prompt used in the large model prediction process, and the specific parameter information can be set according to actual needs, and this example does not impose special restrictions on this; secondly, after preprocessing, the corresponding regional basic information to be predicted and the context information to be predicted can be generated.

[0095] Step S720, performing word embedding processing on the to-be-predicted region basic information based on the embedding mapping layer to obtain a first region feature, and performing embedding mapping processing on the to-be-predicted context information based on the embedding mapping layer to obtain a context marker sequence.

[0096] Specifically, the embedding mapping layer recorded here may include an Embedding embedding mapping layer; at the same time, in the actual application process, for the basic information of the area to be predicted, the embedding mapping processing can be directly performed based on the Embedding embedding mapping layer; for the context information to be predicted, the context information to be predicted can also be embedded and mapped based on the Embedding embedding mapping layer, so as to obtain a context marker sequence.

[0097] Step S730: encoding the first region feature and the context marker sequence based on the encoding layer to obtain the overall context representation, and predicting the context marker sequence and the overall context representation based on the hybrid expert model layer to obtain the object position prediction result.

[0098] In this example embodiment, first, the first region feature and the context marker sequence are encoded based on the encoding layer to obtain an overall context representation; specifically, the encoding layer recorded here can be a multi-layer bidirectional Transformer; at the same time, the specific value of the bidirectional Transformer can be determined according to actual needs, for example, it can be 3 layers or 4 layers, etc., and this example does not impose any special restrictions on this; secondly, the context marker sequence and the overall context representation are predicted based on the hybrid expert model layer to obtain an object position prediction result; specifically, it can be achieved in the following way: based on the gated network model, according to the context marker sequence, the model weight of the expert neural network model is determined, and according to the model weight, the target neural network model required to perform the object position prediction task is determined from the expert neural network; the context marker sequence and the overall context representation are input into the target neural network model to obtain the object position prediction result.

[0099] In an exemplary embodiment, determining the model weight of the expert neural network model according to the context flag sequence based on the gating network model, and determining the target neural network model required to perform the object position prediction task from the expert neural network according to the model weight can be achieved in the following manner: determining the first model weight of the expert neural network model in the object configuration density dimension according to the context flag sequence based on the first gating network model, and determining the first target neural network model required to perform the object position prediction task in the object configuration density dimension from the expert neural network according to the first model weight; determining the second model weight of the expert neural network model in the object configuration breadth dimension according to the context flag sequence based on the second gating network model, and determining the second target neural network model required to perform the object position prediction task in the object configuration breadth dimension from the expert neural network according to the second model weight. That is, in the process of actual application, in order to further improve the accuracy of the object position prediction results, and then improve the user experience on the basis of improving resource utilization, it is necessary to comprehensively consider the two dimensions of object configuration density and configuration breadth; among them, the configuration density recorded here can be used to characterize the distance between two objects; the configuration breadth recorded here can be used to characterize the coverage of the configured objects.

[0100] In an exemplary embodiment, the context marker sequence and the overall context representation are input into the target neural network model to obtain the object position prediction result, which can be achieved in the following manner: input the context marker sequence and the overall context representation into the first target neural network model to obtain a first prediction result in the object configuration dimension; input the context marker sequence and the overall context representation into the second target neural network model to obtain a second prediction result in the object configuration breadth dimension; configure a first dimension weight value for the first prediction result in the object configuration density dimension, and configure a second dimension weight value for the second prediction result in the object configuration breadth dimension; perform weighted summation of the first dimension weight value and the first prediction result, the second dimension weight value and the second prediction result to obtain the object position prediction result.

[0101] In step S130, the object position prediction result is scored based on a preset object position recommendation model to obtain a first scoring result, and the position to be configured of the target object is determined from the object position prediction result according to the first scoring result.

[0102] Specifically, the preset object location recommendation model recorded here can be a deep neural network model (such as a convolutional neural network, a recurrent neural network, or a long short-term memory network, etc.), or a decision tree model (the specific structure can be referred to Figure 6 As shown); At the same time, taking the decision tree model as an example, the specific scoring result can be achieved in the following way: based on the internal nodes of the preset object position recommendation model, the linear regression part of the object position prediction result is calculated; based on the normalization layer where the leaf nodes of the preset object position recommendation model are located, the linear regression part is normalized to obtain the first scoring result.

[0103] Secondly, after obtaining the first scoring result, the object position prediction results can be sorted according to the first scoring result, and then the object position prediction result at the front preset position is taken as the target object to be configured position.

[0104] In step S140, the location of the target object to be configured is uploaded to the blockchain, so that the operation and maintenance personnel can obtain the location of the target object to be configured from the blockchain and perform object configuration.

[0105] Specifically, after obtaining the location of the target object to be configured, the location of the target object to be configured can be uploaded to the blockchain; when the city operation and maintenance personnel need to obtain the information, the location of the target object to be configured can be obtained from the blockchain, and the corresponding personnel can be notified to perform object configuration based on the location of the target object to be configured; based on this, the purpose of improving the user's life experience can be achieved while avoiding waste of object resources.

[0106] The following are embodiments of the device disclosed herein, which can be used to execute the method embodiments disclosed herein. For details not disclosed in the device embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0107] The exemplary embodiment of the present disclosure also provides an application device of data elements in the field of urban governance. Figure 8 As shown, the application device of the data element in the field of urban governance may include a data resource parsing module 810, a location prediction result determination module 820, a to-be-configured location determination module 830, and a to-be-configured location upload module 840. Among them:

[0108] The data resource parsing module 810 can be used to obtain the target data resources of the target area from the blockchain network, and parse the target data resources to obtain the target social demographic data, target area attribute data and target area economic data of the target area;

[0109] The location prediction result determination module 820 may be used to obtain the configured location of the target object in the target area, and input the target socio-demographic data, target area attribute data, target area economic data and the configured location of the target object into a preset object location prediction model to obtain the object location prediction result;

[0110] The module 830 for determining the position to be configured may be used to score the object position prediction result based on a preset object position recommendation model to obtain a first scoring result, and determine the target object position to be configured from the object position prediction result according to the first scoring result;

[0111] The module for uploading the position to be configured 840 may be used to upload the position to be configured of the target object to the blockchain, so that the operation and maintenance personnel can obtain the position to be configured of the target object from the blockchain and perform object configuration.

[0112] In an exemplary embodiment of the present disclosure, the preset object position prediction model includes an embedding mapping layer, a coding layer and a hybrid expert model layer; wherein the target socio-demographic data, target area attribute data, target area economic data and the configured position of the target object are input into the preset object position prediction model to obtain an object position prediction result, including: generating basic regional information to be predicted based on the target socio-demographic data, target area attribute data and target area economic data, and generating context information to be predicted based on the configured position of the target object and preset model prompt parameters; performing word embedding processing on the basic regional information to be predicted based on the embedding mapping layer to obtain a first regional feature, and performing embedding mapping processing on the context information to be predicted based on the embedding mapping layer to obtain a context marker sequence; encoding the first regional feature and the context marker sequence based on the coding layer to obtain a context overall representation, and predicting the context marker sequence and the context overall representation based on the hybrid expert model layer to obtain the object position prediction result.

[0113] In an exemplary embodiment of the present disclosure, the hybrid expert model layer includes a gated network model and an expert neural network model; wherein, the context marker sequence and the overall context representation are predicted based on the hybrid expert model layer to obtain the object position prediction result, including: determining the model weight of the expert neural network model according to the context marker sequence based on the gated network model, and determining the target neural network model required to perform the object position prediction task from the expert neural network according to the model weight; inputting the context marker sequence and the overall context representation into the target neural network model to obtain the object position prediction result.

[0114] In an exemplary embodiment of the present disclosure, the gated network model includes a first gated network model and a second gated network model; wherein, based on the gated network model, according to the context flag sequence, the model weight of the expert neural network model is determined, and according to the model weight, the target neural network model required to perform the object position prediction task is determined from the expert neural network, including: based on the first gated network model, according to the context flag sequence, the first model weight of the expert neural network model in the object configuration density dimension is determined, and according to the first model weight, the first target neural network model required to perform the object position prediction task in the object configuration density dimension is determined from the expert neural network; based on the second gated network model, according to the context flag sequence, the second model weight of the expert neural network model in the object configuration breadth dimension is determined, and according to the second model weight, the second target neural network model required to perform the object position prediction task in the object configuration breadth dimension is determined from the expert neural network.

[0115] In an exemplary embodiment of the present disclosure, the context marker sequence and the overall context representation are input into the target neural network model to obtain the object position prediction result, including: inputting the context marker sequence and the overall context representation into the first target neural network model to obtain a first prediction result in the object configuration dimension; inputting the context marker sequence and the overall context representation into the second target neural network model to obtain a second prediction result in the object configuration breadth dimension; configuring a first dimension weight value for the first prediction result in the object configuration density dimension, and configuring a second dimension weight value for the second prediction result in the object configuration breadth dimension; performing weighted summation of the first dimension weight value and the first prediction result, the second dimension weight value and the second prediction result to obtain the object position prediction result.

[0116] In an exemplary embodiment of the present disclosure, the object position prediction result is scored based on a preset object position recommendation model to obtain a first scoring result, including: calculating the linear regression part of the object position prediction result based on the internal nodes of the preset object position recommendation model; and normalizing the linear regression part based on the normalization layer where the leaf nodes of the preset object position recommendation model are located to obtain the first scoring result.

[0117] In an exemplary embodiment of the present disclosure, the preset object position prediction model is obtained in the following manner: obtaining current socio-demographic data, current regional attribute data and current regional economic data of the object configured area, and determining a first object configuration position of the object configured area before the object position is adjusted and a second object configuration position after the object position is adjusted; inputting the current socio-demographic data, current regional attribute data, current regional economic data and the first object configuration position into a large model to be trained, and obtaining a first prediction result in the object configuration density dimension and a second prediction result in the object configuration breadth dimension; constructing a first loss function based on the second configuration density in the second object configuration position and the first prediction result, and constructing a second loss function based on the second configuration breadth in the second object configuration position and the second prediction result; constructing a target loss function based on the first loss function and the second loss function, and adjusting the parameters in the large model to be trained based on the target loss function to obtain the preset object position prediction model.

[0118] The specific details of each module in the application device of the above-mentioned data elements in the field of urban governance have been described in detail in the corresponding application method of the data elements in the field of urban governance, so they will not be repeated here.

[0119] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0120] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0121] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided. A person skilled in the art will appreciate that various aspects of the present disclosure may be implemented as a system, method, or program product. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, which may be collectively referred to as a "circuit", "module", or "system", etc.

[0122] Refer to the following Fig. 9 The electronic device 900 according to this embodiment of the present disclosure is described. Fig. 9 The electronic device 900 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0123] like Fig. 9 As shown, the electronic device 900 is in the form of a general computing device. The components of the electronic device 900 may include but are not limited to: at least one processing unit 910, at least one storage unit 920, a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910), and a display unit 940.

[0124] The storage unit stores a program code, which can be executed by the processing unit 910, so that the processing unit 910 performs the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 910 can perform the following steps: Figure 1 Step S110 shown in: obtaining target data resources of a target area from a blockchain network, and parsing the target data resources to obtain target socio-demographic data, target area attribute data, and target area economic data of the target area; step S120: obtaining the configured position of a target object in the target area, and inputting the target socio-demographic data, target area attribute data, target area economic data, and the configured position of the target object into a preset object position prediction model to obtain an object position prediction result; step S130: scoring the object position prediction result based on a preset object position recommendation model to obtain a first scoring result, and determining the target object position to be configured from the object position prediction result according to the first scoring result; step S140: uploading the target object position to be configured to the blockchain, so that operation and maintenance personnel can obtain the target object position to be configured from the blockchain and perform object configuration.

[0125] The storage unit 920 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 9201 and / or a cache storage unit 9202 , and may further include a read-only storage unit (ROM) 9203 .

[0126] The storage unit 920 may also include a program / utility 9204 having a set (at least one) of program modules 9205, such program modules 9205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0127] Bus 930 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0128] The electronic device 900 may also communicate with one or more external devices 1000 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 900, and / or communicate with any device that enables the electronic device 900 to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication may be performed through an input / output (I / O) interface 950. In addition, the electronic device 900 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 960. As shown, the network adapter 960 communicates with other modules of the electronic device 900 through a bus 930. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0129] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0130] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above "Exemplary Method" section of the present specification.

[0131] refer to Fig.10As shown, a program product 1010 for implementing the above method according to an embodiment of the present disclosure is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0132] The program product may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0133] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0134] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0135] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0136] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0137] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the inventions invented herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not invented by the present disclosure. The specification and examples are to be considered merely exemplary, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A method for applying data elements in the field of urban governance, characterized in that: Used to configure the position of an object in a smart property scene, wherein the object in the smart property scene includes at least one of a street lamp, a green plant, a trash can, a leisure area, a roadblock, and a parking lot, and the application method includes: Obtaining target data resources of the target area from the blockchain network, and parsing the target data resources to obtain target social demographic data, target area attribute data, and target area economic data of the target area; The configured position of the target object in the target area is obtained, and the target socio-demographic data, the target area attribute data, the target area economic data and the configured position of the target object are input into a preset object position prediction model to obtain an object position prediction result; wherein the preset object position prediction model includes an embedding mapping layer, a coding layer and a hybrid expert model layer, and the hybrid expert model layer includes a gated network model and an expert neural network model; the object position prediction result is obtained in the following manner: basic regional information to be predicted is generated according to the target socio-demographic data, the target area attribute data and the target area economic data, and contextual information to be predicted is generated according to the configured position of the target object and preset model prompt parameters ; Based on the embedding mapping layer, the basic information of the region to be predicted is subjected to word embedding processing to obtain a first region feature, and based on the embedding mapping layer, the context information to be predicted is subjected to embedding mapping processing to obtain a context marker sequence; Based on the encoding layer, the first region feature and the context marker sequence are encoded to obtain a context overall representation, and based on the gated network model, the model weight of the expert neural network model is determined according to the context marker sequence, and the target neural network model required to perform the object position prediction task is determined from the expert neural network according to the model weight; the context marker sequence and the context overall representation are input into the target neural network model to obtain the object position prediction result; Scoring the object position prediction result based on a preset object position recommendation model to obtain a first scoring result, and determining the target object to-be-configured position from the object position prediction result according to the first scoring result; Uploading the target object's to-be-configured location to the blockchain, so that the operation and maintenance personnel can obtain the target object's to-be-configured location from the blockchain and perform object configuration; Among them, the preset object position prediction model is obtained in the following manner: obtaining the current socio-demographic data, current regional attribute data and current regional economic data of the object configured area, and determining the first object configuration position of the object configured area before the object position is adjusted and the second object configuration position after the object position is adjusted; inputting the current socio-demographic data, current regional attribute data, current regional economic data and the first object configuration position into the large model to be trained, and obtaining the first prediction result in the object configuration density dimension and the second prediction result in the object configuration breadth dimension; constructing a first loss function according to the second configuration density in the second object configuration position and the first prediction result, and constructing a second loss function according to the second configuration breadth in the second object configuration position and the second prediction result; constructing a target loss function based on the first loss function and the second loss function, and adjusting the parameters in the large model to be trained based on the target loss function to obtain the preset object position prediction model.

2. The method for applying data elements in the field of urban governance according to claim 1 is characterized in that: The gated network model includes a first gated network model and a second gated network model; Wherein, determining the model weight of the expert neural network model according to the contextual marker sequence based on the gated network model, and determining the target neural network model required to perform the object position prediction task from the expert neural network according to the model weight, includes: Determine a first model weight of the expert neural network model in the object configuration density dimension based on the first gating network model according to the contextual flag sequence, and determine a first target neural network model required to perform the object position prediction task in the object configuration density dimension from the expert neural network according to the first model weight; Based on the second gating network model, according to the context flag sequence, the second model weight of the expert neural network model in the object configuration breadth dimension is determined, and according to the second model weight, the second target neural network model required to perform the object position prediction task in the object configuration breadth dimension is determined from the expert neural network.

3. The method for applying data elements in the field of urban governance according to claim 2 is characterized in that: Inputting the context marker sequence and the overall context representation into the target neural network model to obtain the object position prediction result includes: Inputting the context marker sequence and the overall context representation into the first target neural network model to obtain a first prediction result in the object configuration density dimension; Inputting the contextual marker sequence and the overall context representation into the second target neural network model to obtain a second prediction result in the object configuration breadth dimension; Configure a first dimension weight value for a first prediction result in the object configuration density dimension, and configure a second dimension weight value for a second prediction result in the object configuration breadth dimension; The first dimension weight value and the first prediction result, the second dimension weight value and the second prediction result are weightedly summed to obtain the object position prediction result.

4. The method for applying data elements in the field of urban governance according to claim 1 is characterized in that: Scoring the object position prediction result based on a preset object position recommendation model to obtain a first scoring result includes: Calculate the linear regression part of the object position prediction result based on the internal nodes of the preset object position recommendation model; The linear regression part is normalized based on the normalization layer where the leaf node of the preset object position recommendation model is located to obtain the first scoring result.

5. A device for applying data elements in the field of urban governance, characterized in that: Used to configure the position of an object in a smart property scene, wherein the object in the smart property scene includes at least one of a street lamp, a green plant, a trash can, a leisure area, a roadblock, and a parking lot, and the application device includes: A data resource parsing module, used to obtain target data resources of a target area from a blockchain network, and parse the target data resources to obtain target social demographic data, target area attribute data, and target area economic data of the target area; The position prediction result determination module is used to obtain the configured position of the target object in the target area, and input the target social demographic data, target area attribute data, target area economic data and the configured position of the target object into a preset object position prediction model to obtain the object position prediction result; wherein the preset object position prediction model includes an embedding mapping layer, a coding layer and a hybrid expert model layer, and the hybrid expert model layer includes a gated network model and an expert neural network model; the object position prediction result is obtained in the following manner: generating the basic information of the area to be predicted according to the target social demographic data, the target area attribute data and the target area economic data, and generating the area to be predicted according to the configured position of the target object and the preset model prompt parameters The method comprises the following steps: performing word embedding processing on the basic information of the region to be predicted based on the embedding mapping layer to obtain a first region feature, and performing embedding mapping processing on the context information to be predicted based on the embedding mapping layer to obtain a context marker sequence; encoding the first region feature and the context marker sequence based on the encoding layer to obtain a context overall representation, and determining the model weight of the expert neural network model based on the context marker sequence based on the gated network model, and determining the target neural network model required to perform the object position prediction task from the expert neural network based on the model weight; inputting the context marker sequence and the context overall representation into the target neural network model to obtain the object position prediction result; a module for determining a position to be configured, configured to score the object position prediction result based on a preset object position recommendation model to obtain a first scoring result, and determine the target object position to be configured from the object position prediction result according to the first scoring result; A module for uploading the position to be configured, used to upload the position to be configured of the target object to the blockchain, so that the operation and maintenance personnel can obtain the position to be configured of the target object from the blockchain and perform object configuration; Among them, the preset object position prediction model is obtained in the following manner: obtaining the current socio-demographic data, current regional attribute data and current regional economic data of the object configured area, and determining the first object configuration position of the object configured area before the object position is adjusted and the second object configuration position after the object position is adjusted; inputting the current socio-demographic data, current regional attribute data, current regional economic data and the first object configuration position into the large model to be trained, and obtaining the first prediction result in the object configuration density dimension and the second prediction result in the object configuration breadth dimension; constructing a first loss function according to the second configuration density in the second object configuration position and the first prediction result, and constructing a second loss function according to the second configuration breadth in the second object configuration position and the second prediction result; constructing a target loss function based on the first loss function and the second loss function, and adjusting the parameters in the large model to be trained based on the target loss function to obtain the preset object position prediction model.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the method for applying the data elements described in any one of claims 1 to 4 in the field of urban governance.

7. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the application method of the data elements described in any one of claims 1-4 in the field of urban governance by executing the executable instructions.

Images