Cable line optimization method, device and equipment based on artificial intelligence inference model

Abstract

Embodiments of the present disclosure disclose a cable line optimization method and device based on an artificial intelligence inference model. A specific embodiment of the method includes: obtaining each candidate cable passing point identifier; obtaining each geographic space feature information; performing line optimization data extraction processing on each geographic space feature information; obtaining cable passing point identifier directed graph data; traversing the cable passing point identifier directed graph corresponding to the cable passing point identifier directed graph data; performing optimization processing on each initial cable line information to obtain optimized cable line information corresponding to a preset cable terminal field identifier group; generating cable line laying information; generating cable laying mode information corresponding to the optimized cable line information; determining the optimized cable line information and the cable laying mode information as cable line information, and displaying the cable line information on a preset cable line optimization page. This embodiment improves the experience of cable construction users.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of computer technology, and particularly to a cable line optimization method and device based on an artificial intelligence inference model. BACKGROUND

[0002] With the development of society and industry, the increasing demand for electricity makes the design and planning of cable lines particularly important. The optimization of cable lines based on an artificial intelligence inference model is a technology for generating cable line information. Currently, when generating cable line information, the commonly used method is to directly take the identifiers of each passing point on the shortest distance path between the starting point of the cable terminal field and the terminal of the cable terminal field as the cable line information.

[0003] However, when the above method is used to generate cable line information, the following technical problems often exist:

[0004] Directly taking the identifiers of each passing point on the shortest distance path between the starting point of the cable terminal field and the terminal of the cable terminal field as the cable line information does not consider the influence of geographic spatial feature information on the cable line. The shortest path may pass through complex terrain or obstacles, increasing the difficulty and risk of construction, and making the usability of the cable line information poor. At the same time, directly taking the identifiers of each passing point on the shortest distance path between the starting point of the cable terminal field and the terminal of the cable terminal field as the cable line information does not generate a cable laying method for the cable line according to the geographic spatial feature information of each passing point, resulting in a poor experience for cable construction users.

[0005] The above information disclosed in this BACKGROUND section is only for the purpose of enhancing the understanding of the background of the present inventive concepts, and therefore, it can contain information that is not prior art known to those of ordinary skill in the art. SUMMARY

[0006] The summary of the present disclosure is intended to introduce the concepts in a simplified form, which will be described in detail in the specific embodiments section. The summary of the present disclosure is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0007] Some embodiments of the present disclosure propose a cable line information generation method, device, electronic equipment and computer readable medium to solve one or more of the technical problems mentioned in the background section.

[0008] In a first aspect, some embodiments of the present disclosure provide a cable line optimization method based on an artificial intelligence inference model, the method comprising: obtaining each candidate cable passing point identifier corresponding to a preset cable terminal field identifier group, wherein the preset cable terminal field identifier group comprises a cable terminal field starting point identifier and a cable terminal field ending point identifier; obtaining each geographic space feature information corresponding to each candidate cable passing point identifier from a preset database, wherein each geographic space feature information in the each geographic space feature information comprises passing point terrain elevation information, passing point underground pipeline information, passing point soil condition information, passing point house distribution map, and contaminated area grid data; performing line optimization data extraction processing on the each geographic space feature information to obtain a line optimization extraction data set corresponding to each candidate cable passing point identifier; obtaining pre-constructed cable passing point identifier directed graph data corresponding to the preset cable terminal field identifier group and the each candidate cable passing point identifier from the preset database; traversing a cable passing point identifier directed graph corresponding to the cable passing point identifier directed graph data to obtain each initial cable line information corresponding to the preset cable terminal field identifier group; performing optimization processing on the each initial cable line information based on the line optimization extraction data set and a pre-trained artificial intelligence inference model to obtain optimized cable line information corresponding to the preset cable terminal field identifier group; generating cable line laying information corresponding to the optimized cable line information based on the each geographic space feature information; generating cable laying mode information corresponding to the optimized cable line information based on the cable line laying information; determining the optimized cable line information and the cable laying mode information as cable line information, and displaying the cable line information on a preset cable line optimization page.

[0009] In a second aspect, some embodiments of the present disclosure provide a cable line optimization device based on an artificial intelligence inference model. The device comprises: a first obtaining unit configured to obtain each candidate cable passing point identifier corresponding to a preset cable terminal field identifier set, wherein the preset cable terminal field identifier set comprises a cable terminal field start point identifier and a cable terminal field end point identifier; a second obtaining unit configured to obtain, from a preset database, each geographic space feature information corresponding to each candidate cable passing point identifier, wherein each geographic space feature information in the each geographic space feature information comprises passing point terrain elevation information, passing point underground pipeline information, passing point soil condition information, passing point house distribution map, and contaminated area grid data; an extraction processing unit configured to perform line optimization data extraction processing on the each geographic space feature information to obtain a line optimization extraction data set corresponding to each candidate cable passing point identifier; a third obtaining unit configured to obtain, from the preset database, pre-constructed cable passing point identifier directed graph data corresponding to the preset cable terminal field identifier set and each candidate cable passing point identifier; a traversal unit configured to traverse a cable passing point identifier directed graph corresponding to the cable passing point identifier directed graph data to obtain each initial cable line information corresponding to the preset cable terminal field identifier set; an optimization processing unit configured to perform optimization processing on the each initial cable line information based on the line optimization extraction data set and a pre-trained artificial intelligence inference model to obtain optimized cable line information corresponding to the preset cable terminal field identifier set; a first generation unit configured to generate cable line laying information corresponding to the optimized cable line information based on the each geographic space feature information; a second generation unit configured to generate cable laying mode information corresponding to the optimized cable line information based on the cable line laying information; and a display unit configured to determine the optimized cable line information and the cable laying mode information as cable line information and display the cable line information on a preset cable line optimization page.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; and a storage device having one or more programs stored thereon, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method described in any implementation manner of the first aspect.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any implementation manner of the first aspect.

[0012] The above various embodiments of the present disclosure have the following beneficial effects: through the cable line optimization method based on the artificial intelligence inference model of some embodiments of the present disclosure, the availability of cable line information and the experience of cable construction users are improved. Specifically, the reason why the availability of cable line information and the experience of cable construction users are poor is that: directly taking the identities of each passing point of the shortest distance path between the starting point of the cable terminal field and the terminal end point of the cable terminal field as the cable line information, without considering the influence of geographic spatial feature information on the cable line, the shortest path may pass through complex terrain or obstacles, increasing the difficulty and risk of construction, making the availability of cable line information poor. At the same time, directly taking the identities of each passing point of the shortest distance path between the starting point of the cable terminal field and the terminal end point of the cable terminal field as the cable line information, without generating the cable laying mode for the cable line according to the geographic spatial feature information of each passing point, resulting in poor experience of cable construction users. Based on this, the cable line optimization method based on the artificial intelligence inference model of some embodiments of the present disclosure, first, obtains each candidate cable passing point identifier corresponding to a preset cable terminal field identifier group, wherein the preset cable terminal field identifier group includes a cable terminal field starting point identifier and a cable terminal field terminal end point identifier. In this way, the cable terminal field starting point and the cable terminal field terminal end point and each candidate cable passing point identifier of each passing point between the two points can be obtained. Then, each geographic spatial feature information corresponding to each candidate cable passing point identifier is obtained from a preset database, wherein each geographic spatial feature information in the geographic spatial feature information includes passing point terrain elevation information, passing point underground pipeline information, passing point soil condition information, passing point house distribution map, and pollution area grid data. In this way, each geographic spatial feature information of the cable terminal field starting point and the cable terminal field terminal end point and each passing point between the two points can be obtained. Then, the line optimization data extraction processing is performed on the above-mentioned each geographic spatial feature information to obtain a line optimization extraction data set corresponding to the above-mentioned each candidate cable passing point identifier. In this way, data extraction can be performed on each geographic spatial feature information to obtain a line optimization extraction data set that affects the cable line. Next, the pre-constructed cable passing point identifier directed graph data corresponding to the above-mentioned preset cable terminal field identifier group and the above-mentioned each candidate cable passing point identifier is obtained from the above-mentioned preset database. In this way, the cable passing point identifier directed graph data representing the connection relationship between the preset cable terminal field identifier group and the above-mentioned each candidate cable passing point identifier can be obtained. Then, the cable passing point identifier directed graph corresponding to the cable passing point identifier directed graph data is traversed to obtain each initial cable line information corresponding to the above-mentioned preset cable terminal field identifier group. In this way, each initial cable line information representing all passing lines between the cable terminal field starting point and the cable terminal field terminal end point can be obtained.Afterwards, based on the line optimization extraction data set and the pre-trained artificial intelligence inference model, the initial cable line information is optimized to obtain the optimized cable line information corresponding to the preset cable terminal field identification group. In this way, the initial cable line information can be optimized by the line optimization extraction data set and the pre-trained artificial intelligence inference model that affect the cable line, and the optimized cable line information with high availability can be obtained. Afterwards, based on the geographical space feature information, the cable line laying information corresponding to the optimized cable line information is generated. In this way, the cable line laying information for generating the cable laying mode information can be obtained. Then, based on the cable line laying information, the cable laying mode information corresponding to the optimized cable line information is generated. In this way, the cable laying mode information suitable for the optimized cable line information can be generated. The optimized cable line information and the cable laying mode information are determined as the cable line information, and the cable line information is displayed on the preset cable line optimization page. In this way, the cable line information including the optimized cable line information and the cable laying mode information can be displayed on the preset cable line optimization page, and the experience of the cable construction user is improved. BRIEF DESCRIPTION OF DRAWINGS

[0013] The above and other features, aspects, and advantages of various embodiments of the present disclosure will become more apparent with reference to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals can refer to the same or similar elements. It should be understood that the drawings are schematic and elements and features are not necessarily to scale.

[0014] Figure 1 is a flowchart of some embodiments of a cable line optimization method based on an artificial intelligence inference model according to the present disclosure;

[0015] Figure 2 is a structural schematic diagram of some embodiments of a cable line optimization device based on an artificial intelligence inference model according to the present disclosure;

[0016] Figure 3 is a structural schematic diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings. While several embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be interpreted as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] It should be noted that only parts related to the present application are shown in the drawings for the purpose of description. The embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0019] It should be noted that the terms "first", "second" and the like in the present disclosure are merely used to distinguish different devices, modules or units, and do not imply the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the terms "one", "multiple" in the present disclosure are illustrative and not restrictive, and those skilled in the art should understand that "one" or "multiple" should be understood as "one or more" unless otherwise explicitly indicated in the context.

[0021] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are merely used for illustrative purposes, and are not used to limit the scope of the messages or information.

[0022] The present disclosure will be described in detail below with reference to the drawings and in conjunction with embodiments.

[0023] Figure 1 Flow 100 of some embodiments of a cable route optimization method based on an artificial intelligence inference model according to the present disclosure is shown. The cable route optimization method based on an artificial intelligence inference model includes the following steps:

[0024] Step 101, obtaining each candidate cable passing point identifier corresponding to a preset cable terminal field identifier group.

[0025] In some embodiments, the execution subject (for example, a computing device) of the cable route optimization method based on an artificial intelligence inference model can obtain each candidate cable passing point identifier corresponding to a preset cable terminal field identifier group through wired or wireless connection. Wherein, the preset cable terminal field identifier group includes a cable terminal field start point identifier and a cable terminal field end point identifier. In practice, the execution subject can obtain each candidate cable passing point identifier corresponding to the preset cable terminal field identifier group from a preset database (for example, a relational database) or a preset power management system. The cable terminal field start point identifier can be the identifier (for example, the cable terminal station name) of the cable terminal station at the start point of the cable line. The cable terminal field end point identifier can be the identifier of the cable terminal station at the end point of the cable line. Each candidate cable passing point identifier can be the identifier of the location of each possible route between the cable terminal station at the start point of the cable line and the cable terminal station at the end point of the cable line.

[0026] It should be noted that the wireless connection mode described above can include, but is not limited to, 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other now known or future developed wireless connection modes.

[0027] Step 102, obtaining each geographic spatial feature information corresponding to each candidate cable passing point identifier from a preset database.

[0028] In some embodiments, the execution subject described above can obtain each geographic spatial feature information corresponding to each candidate cable passing point identifier from a preset database. Each geographic spatial feature information in the geographic spatial feature information includes passing point terrain elevation information, passing point underground pipeline information, passing point soil condition information, passing point house distribution map, and pollution area grid data. The preset database can be a geographic information system (GIS) database. Each candidate cable passing point identifier corresponds to each geographic spatial feature information. The passing point terrain elevation information can represent the terrain elevation condition of the passing point. For example, the passing point terrain elevation information can be the average elevation value of the passing point terrain, and the passing point terrain elevation information can be "average elevation value: 15m". The passing point underground pipeline information can represent the underground pipeline data of the underground buried pipeline condition of the passing point. The passing point underground pipeline information can be text information. For example, the passing point underground pipeline information can be "underground pipeline data: one water supply pipe with a diameter of 300mm, buried depth: 1.5m; one gas pipeline with a diameter of 100mm, buried depth: 1.2m;". The passing point soil condition information can represent the soil condition of the passing point. The passing point soil condition information can be text information. For example, the passing point soil condition information can be "high aggregate content, suitable for building foundation". The passing point house distribution map can be a top view of the passing point. The pollution area grid data can represent the pollution degree or pollution source of different positions of the passing point. For example, the pollution area grid data can be "pixel position (1, 1), pollution concentration: 30(mg / L), pollution source: chemical plant wastewater; pixel position (2, 1), pollution concentration: 15(mg / L), pollution source: agricultural runoff; pixel position (1, 2), pollution concentration: 0, pollution source: no pollution; pixel position (2, 2), pollution concentration: 35(mg / L), pollution source: chemical plant wastewater".

[0029] Step 103, performing line optimization data extraction processing on each geographic spatial feature information to obtain a line optimization extraction data set corresponding to each candidate cable passing point identifier.

[0030] In some embodiments, the execution subject can perform line optimization data extraction processing on each of the above-mentioned geographic spatial feature information, to obtain a line optimization extraction data set corresponding to each of the above-mentioned candidate cable passing point identifiers.

[0031] In some optional implementations of some embodiments, the execution subject can perform line optimization data extraction processing on each of the above-mentioned geographic spatial feature information, to obtain a line optimization extraction data set corresponding to each of the above-mentioned candidate cable passing point identifiers, by the following steps:

[0032] First, for each of the above-mentioned geographic spatial feature information, the following extraction steps are performed:

[0033] First sub-step, determine the passing point terrain elevation information included in the above-mentioned geographic spatial feature information as the target passing point terrain elevation information.

[0034] Second sub-step, determine the passing point underground pipeline information included in the above-mentioned geographic spatial feature information as the target passing point underground pipeline information.

[0035] Third sub-step, determine the passing point house distribution map included in the above-mentioned geographic spatial feature information as the to-be-extracted house distribution map.

[0036] Fourth sub-step, perform recognition extraction processing on the above-mentioned to-be-extracted house distribution map to obtain the passing point house distribution quantity. In practice, the above-mentioned can recognize the number of houses in the to-be-extracted house distribution map as the passing point house distribution quantity through the pre-trained house quantity recognition model. Wherein, the above-mentioned pre-trained house quantity recognition model can be a YOLO model that takes the to-be-extracted house distribution map as input and takes the house quantity as output. Optionally, the execution subject can also recognize the number of houses in the to-be-extracted house distribution map through template matching technology.

[0037] Fifth sub-step, determine the above-mentioned target passing point terrain elevation information, the above-mentioned target passing point underground pipeline information and the above-mentioned passing point house distribution quantity as the line optimization extraction data corresponding to the above-mentioned geographic spatial feature information.

[0038] Second, determine each of the determined line optimization extraction data as the line optimization extraction data set. Wherein, each of the line optimization extraction data in the line optimization extraction data set corresponds to each of the above-mentioned candidate cable passing point identifiers.

[0039] Step 104, obtain the pre-constructed cable passing point identifier directed graph data corresponding to the preset cable terminal field identifier group and each candidate cable passing point identifier from the preset database.

[0040] In some embodiments, the execution subject can obtain pre-constructed cable route point identifier directed graph data corresponding to the preset cable terminal field identifier group and the respective candidate cable passing point identifiers from the preset database. The cable route point identifier directed graph data can represent a cable route point identifier directed graph. Each identifier of each node in the cable route point identifier directed graph includes a respective candidate cable passing point identifier, a cable terminal field start point identifier, and a cable terminal field end point identifier. The cable route point identifier directed graph can represent a directed graph of connection relationships between nodes corresponding to respective candidate cable passing point identifiers, a cable terminal field start point identifier, and a cable terminal field end point identifier. For example, the cable terminal field start point identifier and the cable terminal field end point identifier can be represented by identifier A and identifier D, respectively, and the respective candidate cable passing point identifiers can be represented by identifier C and identifier B. The cable route point identifier directed graph data can be represented as "'identifier A': ['identifier B', 'identifier C'], 'identifier B': ['identifier D'], 'identifier C': ['identifier D']".

[0041] In step 105, the execution subject traverses the cable route point identifier directed graph corresponding to the cable route point identifier directed graph data to obtain respective initial cable line information corresponding to the preset cable terminal field identifier group.

[0042] In some embodiments, the execution subject can traverse the cable route point identifier directed graph corresponding to the cable route point identifier directed graph data to obtain respective initial cable line information corresponding to the preset cable terminal field identifier group. Each initial cable line information includes a cable passing point identifier sequence, and the cable passing point identifier sequence includes respective cable passing point identifiers, including respective candidate cable passing point identifiers, a cable terminal field start point identifier, and a cable terminal field end point identifier. In practice, the execution subject can traverse the cable route point identifier directed graph corresponding to the cable route point identifier directed graph data by using a depth-first search (DFS) algorithm to obtain respective initial cable line information corresponding to the preset cable terminal field identifier group.

[0043] In some optional implementations of some embodiments, the execution subject can traverse the cable route point identifier directed graph corresponding to the cable route point identifier directed graph data to obtain respective initial cable line information corresponding to the preset cable terminal field identifier group by the following steps:

[0044] First, the cable terminal field start point identifier in the cable route point identifier directed graph is added to a first preset sequence.

[0045] Secondly, each node identifier corresponding to each direct successor node of the node corresponding to the cable terminal field start point identifier identified by the cable passing point identifier is determined as each target candidate cable passing point identifier. Each direct successor node of the node corresponding to the cable terminal field start point identifier can be directly reached by the node corresponding to the cable terminal field start point identifier through a single directed edge.

[0046] Thirdly, based on each target candidate cable passing point identifier and the first preset sequence, the following determination step is performed:

[0047] Firstly, for each target candidate cable passing point identifier, the following steps are performed:

[0048] Sub-step one, in response to determining that the target candidate cable passing point identifier is the cable terminal field end point identifier, the target candidate cable passing point identifier is added to the first preset sequence to obtain a target first preset sequence.

[0049] Sub-step two, in response to determining that the target candidate cable passing point identifier is not the cable terminal field end point identifier, the following steps are performed:

[0050] First sub-step, the target candidate cable passing point identifier is added to the first preset sequence to update the first preset sequence.

[0051] Second sub-step, in response to determining that each candidate cable passing point identifier corresponding to each direct successor node of the node corresponding to the target candidate cable passing point identifier in the cable passing point identifier directed graph is not empty, each candidate cable passing point identifier corresponding to each direct successor node of the node corresponding to the target candidate cable passing point identifier in the cable passing point identifier directed graph is determined as each target candidate cable passing point identifier to update each target candidate cable passing point identifier.

[0052] Third sub-step, according to the updated each target candidate cable passing point identifier and the updated first preset sequence, the above determination step is performed again.

[0053] A second sub-step, determining the determined respective target first preset sequence as respective initial cable line information corresponding to the preset cable terminal field identification group. Each initial cable line information includes a cable passing point identification sequence, the cable passing point identification sequence includes respective cable passing point identifications, and each cable passing point identification includes respective candidate cable passing point identifications, a cable terminal field start point identification, and a cable terminal field end point identification. As an example, the cable passing point identification directed graph data can be represented as "'identification A': ['identification B', 'identification C'], 'identification B': ['identification D'], and 'identification C': ['identification D']". The respective initial cable line information can be "{identification A, identification B, identification D}, {identification A, identification C, identification D}".

[0054] Step 106, based on the line optimization extraction data set and the pre-trained artificial intelligence inference model, optimizing the respective initial cable line information to obtain optimized cable line information corresponding to the preset cable terminal field identification group.

[0055] In some embodiments, the execution subject can optimize the respective initial cable line information based on the line optimization extraction data set and the pre-trained artificial intelligence inference model to obtain optimized cable line information corresponding to the preset cable terminal field identification group.

[0056] Before generating the cable line information, the respective initial cable line information needs to be optimized based on the line optimization extraction data set and the pre-trained artificial intelligence inference model to obtain optimized cable line information corresponding to the preset cable terminal field identification group. Although the optimization of the respective initial cable line information based on the line optimization extraction data set takes into account the influence of geographic spatial feature information on the cable line, it does not take into account the total distance of the line. When the total distance of the cable line corresponding to the optimized cable line information obtained after optimization is too long, it may lead to an increase in cable power transmission loss in the later stage, and the feasibility of the cable line corresponding to the optimized cable line information obtained after optimization is still poor, which requires re-optimization of the respective initial cable line information, wasting computer computing resources.

[0057] To solve the above technical problems, the inventors have decided to adopt the following solutions:

[0058] In some optional implementations of some embodiments, the execution subject can optimize the respective initial cable line information based on the line optimization extraction data set and the pre-trained artificial intelligence inference model to obtain optimized cable line information corresponding to the preset cable terminal field identification group by the following steps:

[0059] The first step, for each of the above initial cable line information, the following steps are performed:

[0060] The first sub-step, the cable passing point identifier sequence included in the above initial cable line information is determined as the reference cable passing point identifier sequence.

[0061] The second sub-step, the distance between each two adjacent reference cable passing point identifiers in the above reference cable passing point identifier sequence is determined. In practice, the above execution subject can call a preset map API interface to determine the distance between each two adjacent reference cable passing point identifiers in the above reference cable passing point identifier sequence. Wherein, the above preset map API interface can be a preset map application interface. As an example, the above reference cable passing point identifier sequence can be {identifier A, identifier C, identifier D}, and the distance between each two adjacent reference cable passing point identifiers can be the distance between the passing points corresponding to identifier A and identifier C, and the distance between the passing points corresponding to identifier C and identifier D.

[0062] The third sub-step, the sum of each distance determined is determined as the total distance information corresponding to the above initial cable line information.

[0063] The fourth sub-step, each line optimization extraction data in the above line optimization extraction data set corresponding to each candidate cable passing point identifier in the above reference cable passing point identifier sequence is determined as the reference line optimization extraction data set corresponding to the above initial cable line information.

[0064] The fifth sub-step, the above total distance information is added to the above reference line optimization extraction data set as reference line optimization extraction data, to update the above reference line optimization extraction data set, to obtain the updated reference line optimization extraction data set corresponding to the above initial cable line information.

[0065] The second step, each updated reference line optimization extraction data set corresponding to the above each initial cable line information is input into the conversion layer of the pre-trained artificial intelligence inference model, to obtain each optimization feature extraction information set corresponding to the above each updated reference line optimization extraction data set. Wherein, the above artificial intelligence inference model includes the above conversion layer, feature fusion layer, fitness prediction layer, output layer. The above conversion layer can be an embedding layer (Embedding Layer) with each updated reference line optimization extraction data set as input data, and each optimization feature extraction information set as output data. Each optimization feature extraction information in the above each optimization feature extraction information set can be a feature vector representing optimization feature extraction information.

[0066] In the third step, for each of the optimization feature extraction information sets, the optimization feature extraction information set is input into the feature fusion layer to obtain fusion feature information corresponding to the optimization feature extraction information set. The feature fusion layer can be a concatenate layer that takes the optimization feature extraction information set as input data and outputs the fusion feature information. The fusion feature information can be a feature vector obtained by concatenating feature vectors representing the optimization feature extraction information sets.

[0067] In the fourth step, each of the obtained fusion feature information is determined as a target fusion feature information. Each of the target fusion feature information corresponds to each of the initial cable line information.

[0068] In the fifth step, each target fusion feature information is input into the fitness prediction layer to obtain each fitness score corresponding to the target fusion feature information. The fitness prediction layer can be a fully connected layer. Each fitness score can represent the comprehensive performance or fitness of the initial cable line information corresponding to the updated reference line optimization extraction dataset. The fitness score can be the sum of the scores corresponding to each updated reference line optimization extraction data in the updated reference line optimization extraction dataset. The fitness prediction layer can be a preset correspondence table. For example, the initial cable line information can be {Identification A, Identification B, Identification D}. The updated reference line optimization extraction dataset corresponding to {Identification A, Identification B, Identification D} can be "terrain elevation information of passing point: average elevation value: 15m, underground pipeline information of passing point: no underground pipeline, number of house distribution of passing point: 0". The updated reference line optimization extraction dataset can be "terrain elevation information of passing point: average elevation value: 15m, underground pipeline information of passing point: no underground pipeline, number of house distribution of passing point: 0, total distance information: 10km". The correspondence table can be that the score corresponding to the average elevation value included in the terrain elevation information of passing point being less than or equal to 15m can be 2, the score corresponding to the average elevation value included in the terrain elevation information of passing point being greater than 15m can be 0. The score corresponding to the underground pipeline information of passing point representing that there is an underground pipeline and the number of underground pipelines being greater than a preset value can be 0, the score corresponding to the underground pipeline information of passing point representing that there is an underground pipeline and the number of underground pipelines being less than or equal to a preset value can be 1, and the score corresponding to the underground pipeline information of passing point representing that there is no underground pipeline can be 2. The score corresponding to the number of house distribution of passing point being less than or equal to a preset number (e.g., 30) can be 2, and the score corresponding to the number of house distribution of passing point being greater than the preset number can be 0. The score corresponding to the distance included in the total distance information being greater than 50km can be 0, and the score corresponding to the distance included in the total distance information being less than or equal to 50km can be 2. Therefore, the fitness score (the sum of the scores corresponding to each updated reference line optimization extraction data) corresponding to "terrain elevation information of passing point: average elevation value: 15m, underground pipeline information of passing point: no underground pipeline, number of house distribution of passing point: 0" and "terrain elevation information of passing point: average elevation value: 15m, underground pipeline information of passing point: no underground pipeline, number of house distribution of passing point: 0, total distance information: 10km" can be 8.

[0069] In the sixth step, the above respective fitness scores and the above respective initial cable line information are input into the output layer to obtain optimized cable line information. The output layer can determine a fitness score that meets a predetermined condition (e.g., the largest fitness score) from the respective fitness scores as a target fitness score, and then output the initial cable line information corresponding to the target fitness score as the optimized cable line information. The artificial intelligence inference model can be a neural network model (e.g., a recurrent neural network (RNN) and its variants (e.g., Long Short Term Memory networks (LSTM))).

[0070] The technical scheme and related content thereof serve as one inventive point of the embodiments of the present disclosure, and solve the technical problem of poor cable line feasibility corresponding to optimized cable line information and waste of computer computing resources. Factors leading to the poor cable line feasibility corresponding to the optimized cable line information and the waste of computer computing resources are often as follows: before the cable line information is generated, the initial cable line information is optimized according to the line optimization extraction data set to obtain the optimized cable line information corresponding to the preset cable terminal field identification group. Although the initial cable line information is optimized according to the line optimization extraction data set, the influence of geographical spatial feature information on the cable line is considered, but the total distance of the line is not considered. When the total distance of the cable line corresponding to the optimized cable line information obtained after optimization is too long, the cable power transmission loss in the later stage may increase, the cable line feasibility corresponding to the optimized cable line information obtained after optimization is still poor, and the computer computing resources are wasted by re-optimizing each initial cable line information. If the above factors are solved, the cable line feasibility corresponding to the optimized cable line information can be improved, and the waste of computer computing resources can be reduced. To achieve this effect, first, for each initial cable line information in the initial cable line information, the following steps are performed: first, the cable passing point identification sequence included in the initial cable line information is determined as a reference cable passing point identification sequence. In this way, the reference cable passing point identification sequence for determining the distance between each passing point corresponding to the initial cable line information can be obtained. Second, the distance between each two adjacent reference cable passing point identification in the reference cable passing point identification sequence is determined. In this way, the distance between each passing point corresponding to the initial cable line information can be obtained. Third, the sum of the distances determined is determined as the total distance information corresponding to the initial cable line information. Fourth, each line optimization extraction data in the line optimization extraction data set corresponding to each candidate cable passing point identification in the reference cable passing point identification sequence is determined as the reference line optimization extraction data set corresponding to the initial cable line information. In this way, the reference line optimization extraction data set for generating the updated reference line optimization extraction data set can be obtained. Fifth, the total distance information is added to the reference line optimization extraction data set as the reference line optimization extraction data to update the reference line optimization extraction data set, and the updated reference line optimization extraction data set corresponding to the initial cable line information is obtained. In this way, the total distance information can be added to the reference line optimization extraction data set. Then, each updated reference line optimization extraction data set corresponding to each initial cable line information is input into the conversion layer of the pre-trained artificial intelligence inference model to obtain each optimized feature extraction information set corresponding to each updated reference line optimization extraction data set.The artificial intelligence inference model includes the conversion layer, the feature fusion layer, the fitness prediction layer, and the output layer. In this way, each updated reference line optimization extraction data set can be converted into an optimization feature extraction information set. Then, for each optimization feature extraction information set in the optimization feature extraction information set, the optimization feature extraction information set is input into the feature fusion layer to obtain a fusion feature information corresponding to the optimization feature extraction information set. In this way, each optimization feature extraction information in the converted optimization feature extraction information set can be fused to obtain a fusion feature information corresponding to the optimization feature extraction information set. Then, each fusion feature information obtained is determined as a target fusion feature information, and each target fusion feature information corresponds to each initial cable line information. Then, each target fusion feature information is input into the fitness prediction layer to obtain a fitness score corresponding to each target fusion feature information. In this way, a fitness score representing the fitness of a cable line corresponding to each initial cable line information under each updated reference line optimization extraction data set can be obtained. Then, each fitness score and each initial cable line information are input into the output layer to obtain an optimized cable line information. In this way, an optimized cable line information with high fitness can be obtained. In addition, each total distance information corresponding to each initial cable line information is determined and added to each reference line optimization extraction data set corresponding to each initial cable line information to obtain each updated reference line optimization extraction data set containing distance information. Then, each updated reference line optimization extraction data set and each initial cable line information are input into the artificial intelligence inference model to obtain an optimized cable line information. The influence of geographic spatial feature information on the cable line is considered, and the influence of total distance information on the cable line is also considered. The feasibility of the cable line corresponding to the optimized cable line information is improved, the number of re-optimization processes of each initial cable line information is reduced, and the waste of computer computing resources is reduced.

[0071] In step 107, cable line laying information corresponding to the optimized cable line information is generated based on each geographic spatial feature information.

[0072] In some embodiments, the execution subject can generate cable line laying information corresponding to the optimized cable line information based on each geographic spatial feature information.

[0073] In some optional implementations of some embodiments, the execution subject can generate cable line laying information corresponding to the optimized cable line information based on each geographic spatial feature information by the following steps:

[0074] In a first step, each of the geographical feature information corresponding to each of the candidate cable passing points included in the optimized cable route information is determined as a reference geographical feature information.

[0075] In a second step, for each of the reference geographical feature information, the soil condition information and the pollution area grid data included in the reference geographical feature information are determined as a cable route laying sub-information.

[0076] In a third step, each of the determined cable route laying sub-information is determined as a cable route laying information corresponding to the optimized cable route information.

[0077] In step 108, based on the cable route laying information, a cable laying manner information corresponding to the optimized cable route information is generated.

[0078] In some embodiments, the execution subject can generate the cable laying manner information corresponding to the optimized cable route information based on the cable route laying information.

[0079] In some optional implementations of some embodiments, the execution subject can generate the cable laying manner information corresponding to the optimized cable route information based on the cable route laying information by the following steps:

[0080] In a first step, the cable route laying information is input into a pre-trained cable laying manner prediction model to obtain the cable laying manner information corresponding to the optimized cable route information. The cable laying manner prediction model can be a neural network model (e.g., a back propagation neural network (BP neural network), a convolutional neural network (CNN)) that takes the cable route laying information as input and outputs the cable laying manner information. The cable laying manner information can be text information representing the cable laying manner. For example, the cable laying manner information can be the manner of laying and installing the cable to form the cable route. For example, the cable laying manner information can be "laying the cable on the pre-set cable bridge".

[0081] Optionally, the cable laying manner prediction model can be trained by the following steps:

[0082] In a first step, a sample set is obtained. The samples in the sample set include sample cable route laying information and sample target cable laying manner information corresponding to the sample cable route laying information.

[0083] In a second step, based on the sample set, the following training steps are performed:

[0084] Sub-step one, inputting the sample cable line laying information of at least one sample in the sample set into the preset initial neural network to obtain the sample predicted cable laying mode information corresponding to each sample in the at least one sample.

[0085] Sub-step two, comparing the sample predicted cable laying mode information corresponding to each sample in the at least one sample with the corresponding sample target cable laying mode information. In practice, the execution subject can compare through a cross-entropy loss function to determine the gap between the sample predicted cable laying mode information corresponding to each sample in the at least one sample and the corresponding sample target cable laying mode information. Wherein, the distance can be represented by cosine similarity.

[0086] Sub-step three, determining whether the preset initial neural network reaches the preset optimization target according to the comparison result. Wherein, the optimization target can be loss function minimization, maximum likelihood function.

[0087] Sub-step four, in response to determining that the preset initial neural network reaches the optimization target, taking the preset initial neural network as the trained cable laying mode prediction model.

[0088] Sub-step five, in response to determining that the preset initial neural network does not reach the optimization target, adjusting the network parameters of the preset initial neural network, and using the unused sample group to form a sample set, using the adjusted preset initial neural network as the preset initial neural network, and executing the above training step again. As an example, the back propagation algorithm (BP algorithm) can be used to adjust the network parameters of the preset initial neural network.

[0089] Step 109, determining the optimized cable line information and the cable laying mode information as the cable line information, and displaying the cable line information on the preset cable line optimization page.

[0090] In some embodiments, the execution subject can determine the optimized cable line information and the cable laying mode information as the cable line information, and display the cable line information on the preset cable line optimization page. Wherein, the preset cable line optimization page can be a page for displaying cable line information.

[0091] The above various embodiments of the present disclosure have the following beneficial effects: through the cable line optimization method based on the artificial intelligence inference model of some embodiments of the present disclosure, the availability of cable line information and the experience of cable construction users are improved. Specifically, the reason why the availability of cable line information and the experience of cable construction users are poor is that: directly taking the identities of each passing point of the shortest distance path between the starting point of the cable terminal field and the terminal end point of the cable terminal field as the cable line information, without considering the influence of geographic spatial feature information on the cable line, the shortest path may pass through complex terrain or obstacles, increasing the difficulty and risk of construction, making the availability of cable line information poor. At the same time, directly taking the identities of each passing point of the shortest distance path between the starting point of the cable terminal field and the terminal end point of the cable terminal field as the cable line information, without generating the cable laying mode for the cable line according to the geographic spatial feature information of each passing point, resulting in poor experience of cable construction users. Based on this, the cable line optimization method based on the artificial intelligence inference model of some embodiments of the present disclosure, first, obtains each candidate cable passing point identifier corresponding to a preset cable terminal field identifier group, wherein the preset cable terminal field identifier group includes a cable terminal field starting point identifier and a cable terminal field terminal end point identifier. In this way, the cable terminal field starting point and the cable terminal field terminal end point and each candidate cable passing point identifier of each passing point between the two points can be obtained. Then, each geographic spatial feature information corresponding to each candidate cable passing point identifier is obtained from a preset database, wherein each geographic spatial feature information in the geographic spatial feature information includes passing point terrain elevation information, passing point underground pipeline information, passing point soil condition information, passing point house distribution map, and pollution area grid data. In this way, each geographic spatial feature information of the cable terminal field starting point and the cable terminal field terminal end point and each passing point between the two points can be obtained. Then, the line optimization data extraction processing is performed on the above-mentioned each geographic spatial feature information to obtain a line optimization extraction data set corresponding to the above-mentioned each candidate cable passing point identifier. In this way, data extraction can be performed on each geographic spatial feature information to obtain a line optimization extraction data set that affects the cable line. Next, the pre-constructed cable passing point identifier directed graph data corresponding to the above-mentioned preset cable terminal field identifier group and the above-mentioned each candidate cable passing point identifier is obtained from the above-mentioned preset database. In this way, the cable passing point identifier directed graph data representing the connection relationship between the preset cable terminal field identifier group and the above-mentioned each candidate cable passing point identifier can be obtained. Then, the cable passing point identifier directed graph corresponding to the cable passing point identifier directed graph data is traversed to obtain each initial cable line information corresponding to the above-mentioned preset cable terminal field identifier group. In this way, each initial cable line information representing all passing lines between the cable terminal field starting point and the cable terminal field terminal end point can be obtained.Afterwards, based on the above line optimization extraction dataset and pre-trained artificial intelligence inference model, the above various initial cable line information is optimized to obtain the optimized cable line information corresponding to the preset cable terminal field identification group. In this way, the initial cable line information can be optimized by the line optimization extraction dataset that affects the cable line, and the optimized cable line information with high availability can be obtained. Afterwards, based on the above various geographic spatial feature information, the cable line laying information corresponding to the above optimized cable line information is generated. In this way, the cable line laying information for generating the cable laying method information can be obtained. Then, based on the above cable line laying information, the cable laying method information corresponding to the above optimized cable line information is generated. In this way, the cable laying method information suitable for the optimized cable line information can be generated. The above optimized cable line information and the above cable laying method information are determined as the cable line information, and the above cable line information is displayed on the preset cable line optimization page. In this way, the cable line information including the optimized cable line information and the cable laying method information can be displayed on the preset cable line optimization page, and the experience of the cable construction user is improved.

[0092] Further reference Figure 2 , as the implementation of the method shown in each figure, the present disclosure provides some embodiments of a cable line optimization device based on artificial intelligence inference model, which device embodiment corresponds to the method embodiment shown in Figure 1 , and the device can be applied in various electronic devices.

[0093] As Figure 2As shown, the cable line optimization apparatus 200 of some embodiments based on artificial intelligence inference model comprises: a first acquisition unit 201, a second acquisition unit 202, an extraction processing unit 203, a third acquisition unit 204, a traversal unit 205, an optimization processing unit 206, a first generation unit 207, a second generation unit 208 and a display unit 209. Among them, the first acquisition unit 201 is configured to acquire each candidate cable passing point identifier corresponding to a preset cable terminal field identifier set, wherein the above-mentioned preset cable terminal field identifier set includes a cable terminal field starting point identifier and a cable terminal field end point identifier; the second acquisition unit 202 is configured to acquire each geographic space feature information corresponding to the above-mentioned each candidate cable passing point identifier from a preset database, wherein each geographic space feature information in the above-mentioned each geographic space feature information includes passing point terrain elevation information, passing point underground pipeline information, passing point soil condition information, passing point house distribution map, and pollution area grid data; the extraction processing unit 203 is configured to perform line optimization data extraction processing on the above-mentioned each geographic space feature information to obtain a line optimization extraction data set corresponding to the above-mentioned each candidate cable passing point identifier; the third acquisition unit 204 is configured to acquire a pre-constructed cable passing point identifier directed graph data corresponding to the above-mentioned preset cable terminal field identifier set and the above-mentioned each candidate cable passing point identifier from the above-mentioned preset database; the traversal unit 205 is configured to traverse the cable passing point identifier directed graph corresponding to the above-mentioned cable passing point identifier directed graph data to obtain each initial cable line information corresponding to the above-mentioned preset cable terminal field identifier set; the optimization processing unit 206 is configured to perform optimization processing on the above-mentioned each initial cable line information based on the above-mentioned line optimization extraction data set and a pre-trained artificial intelligence inference model to obtain optimization cable line information corresponding to the above-mentioned preset cable terminal field identifier set; the first generation unit 207 is configured to generate cable line laying information corresponding to the above-mentioned optimization cable line information based on the above-mentioned each geographic space feature information; the second generation unit 208 is configured to generate cable laying mode information corresponding to the above-mentioned optimization cable line information based on the above-mentioned cable line laying information; the display unit 209 is configured to determine the above-mentioned optimization cable line information and the above-mentioned cable laying mode information as cable line information, and display the above-mentioned cable line information on a preset cable line optimization page.

[0094] It can be understood that the units recorded in the apparatus 200 correspond to the steps in the above-mentioned method. Therefore, the operations, features and beneficial effects described above for the method also apply to the apparatus 200 and the units contained therein, which will not be described here again. Figure 1

[0095] The following refers to Figure 3 , which shows a structural schematic diagram of an electronic device 300 suitable for implementing some embodiments of the present disclosure.​Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0096] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0097] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0098] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0099] Note that the computer-readable medium in some embodiments of the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may, for example and without limitation, be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program used by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, the computer-readable signal medium can include a data signal propagated in baseband or propagated as a carrier wave in a propagated data signal, in which the computer-readable program code is contained. Such a propagated data signal can take a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium that is not a storage medium and that can communicate, propagate, or transport program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained in the computer-readable medium can be transmitted using any suitable medium, including but not limited to wire, cable, RF, etc., or any suitable combination of the foregoing.

[0100] In some embodiments, the client, server, or both can communicate using any current known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet, and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any current known or future developed networks.

[0101] The computer readable medium can be contained in the electronic device; or can exist separately from the electronic device. The computer readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire each candidate cable route point identifier corresponding to a preset cable terminal field identifier group, wherein the preset cable terminal field identifier group includes a cable terminal field start point identifier and a cable terminal field end point identifier; acquire, from a preset database, each geographic space feature information corresponding to the each candidate cable route point identifier, wherein each geographic space feature information in the each geographic space feature information includes route point terrain elevation information, route point underground pipeline information, route point soil condition information, route point house distribution map, and contaminated area grid data; perform line optimization data extraction processing on the each geographic space feature information to obtain a line optimization extraction data set corresponding to the each candidate cable route point identifier; acquire, from the preset database, pre-constructed cable route point identifier directed graph data corresponding to the preset cable terminal field identifier group and the each candidate cable route point identifier; traverse a cable route point identifier directed graph corresponding to the cable route point identifier directed graph data to obtain each initial cable line information corresponding to the preset cable terminal field identifier group; perform optimization processing on the each initial cable line information based on the line optimization extraction data set and a pre-trained artificial intelligence inference model to obtain optimized cable line information corresponding to the preset cable terminal field identifier group; generate cable line laying information corresponding to the optimized cable line information based on the each geographic space feature information; generate cable laying mode information corresponding to the optimized cable line information based on the cable line laying information; determine the optimized cable line information and the cable laying mode information as cable line information, and display the cable line information on a preset cable line optimization page.

[0102] Computer program code for carrying out operations of some embodiments of the present disclosure can be written in one or more programming languages or combinations of languages including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages such as "C" or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0103] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions of the flow diagrams and / or block diagrams as computer processes. In this context, a "computer" apparatus can be a general purpose computing device, a special purpose computing device, a computing device that is integrated into another device (e.g., a computerized television), or a computerized device that is integrated into a computing device (e.g., a television with one or more built-in computers). The processes to be implemented by the various entities described herein can be provided by the computer program instructions which, when processed by a processing device, provide steps for implementing the functions of the various entities described herein. The computer program instructions can be stored in any appropriate data storage medium or memory device, including without limitation semiconductor memory devices, magnetic memory devices and systems, optical memory devices and systems, flash memory, core or other memory technology, CD-ROMs, DVDs or other disc storage, or any other data storage medium or memory device that is suitable for storing the desired instructions.

[0104] The units described in some embodiments of the present disclosure can be implemented in the form of software, or can be implemented in the form of hardware. The described units can also be arranged in a processor, for example, can be described as: a processor comprising a first acquisition unit, a second acquisition unit, an extraction processing unit, a third acquisition unit, a traversal unit, an optimization processing unit, a first generation unit, a second generation unit and a display unit. Among them, the name of these units does not constitute a limitation to the unit itself in some cases, for example, the first generation unit can also be described as "a unit for generating cable route laying information corresponding to the above-mentioned optimized cable route information based on the above-mentioned various geographic spatial feature information".

[0105] The functions described above in the detailed description can be performed in at least partially by one or more hardware logic components. For example, and without limitation, example types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0106] The above description is merely some of the preferred embodiments of the present disclosure and a description of the principles of the technology used. Those skilled in the art should understand that the scope of the application involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combinations of technical features, and should also cover other technical solutions formed by any combination of technical features or their equivalent features without departing from the inventive concept. For example, the technical solutions formed by the mutual replacement of features and the technical features disclosed in the embodiments of the present disclosure (but not limited to) with similar functions.

Claims

1. A cable line optimization method based on an artificial intelligence reasoning model, comprising: Obtain the identifiers of each candidate cable path point corresponding to the preset cable terminal field identifier group, wherein the preset cable terminal field identifier group includes a cable terminal field start point identifier and a cable terminal field end point identifier, wherein the cable terminal field start point identifier is the identifier of the cable terminal station at the start of the cable line, and the cable terminal field end point identifier is the identifier of the cable terminal station at the end of the cable line. Obtain geospatial feature information corresponding to each candidate cable route point identifier from a preset database. Each geospatial feature information includes route point topographic elevation information, route point underground pipeline information, route point soil condition information, route point building distribution map, and contaminated area grid data. The geospatial feature information is processed to extract route optimization data, resulting in a route optimization extraction dataset corresponding to the identifiers of each candidate cable route point. Obtain pre-constructed directed graph data of cable path point identifiers corresponding to the preset cable terminal field identifier group and each candidate cable path point identifier from the preset database; Traverse the directed graph corresponding to the cable path point identifier data to obtain the initial cable line information corresponding to the preset cable terminal field identifier group, including: Add the cable terminal field start point identifier in the directed graph of the cable path point identifier to the first preset sequence; The node identifiers corresponding to each direct successor node of the node corresponding to the starting point node of the cable terminal field in the directed graph of the cable path point identifier are determined as the node identifiers of each target candidate cable path point. Based on the identifiers of each target candidate cable route point and the first preset sequence, the following determination steps are performed: For each target candidate cable path point identifier in the various target candidate cable path point identifiers, perform the following steps: In response to determining that the target candidate cable route point identifier is the cable terminal field end point identifier, the target candidate cable route point identifier is added to the first preset sequence to obtain the target first preset sequence; In response to the determination that the target candidate cable route point identifier is not the cable termination field endpoint identifier, the following steps are performed: Add the target candidate cable route point identifier to the first preset sequence to update the first preset sequence; In response to the fact that the candidate cable path point identifiers corresponding to each direct successor node of the node corresponding to the target candidate cable path point identifier in the directed graph of cable path point identifier are not empty, the candidate cable path point identifiers corresponding to each direct successor node of the node corresponding to the target candidate cable path point identifier in the directed graph of cable path point identifier are determined as the target candidate cable path point identifiers, so as to update the target candidate cable path point identifiers. Based on the updated identifiers of each target candidate cable transit point and the updated first preset sequence, the determination step is executed again; Each of the determined targets is first preset sequence and is identified as each of the initial cable line information corresponding to the preset cable terminal field identification group. Each of the initial cable line information includes a cable path point identification sequence, the cable path point identification sequence includes each cable path point identification, and each cable path point identification includes each candidate cable path point identification, cable terminal field start point identification, and cable terminal field end point identification. Based on the line optimization extraction dataset and the pre-trained artificial intelligence reasoning model, the initial cable line information is optimized to obtain optimized cable line information corresponding to the preset cable terminal field identifier group. Based on the aforementioned geospatial feature information, cable laying information corresponding to the optimized cable line information is generated. Based on the cable line laying information, cable laying method information corresponding to the optimized cable line information is generated; The optimized cable line information and the cable laying method information are identified as cable line information, and the cable line information is displayed on the preset cable line optimization page.

2. The method according to claim 1, wherein, Each candidate cable path point identifier in the candidate cable path point identifiers corresponds one-to-one with each geospatial feature information in the candidate geospatial feature information. The process of extracting route optimization data from the geospatial feature information to obtain a route optimization extraction dataset corresponding to each candidate cable path point identifier includes: For each of the aforementioned geospatial feature information, the following extraction steps are performed: The topographic elevation information of the waypoints included in the geospatial feature information is determined as the topographic elevation information of the target waypoints; The underground pipeline information of the waypoints included in the geospatial feature information is determined as the underground pipeline information of the target waypoints; The distribution map of houses at the waypoints included in the geospatial feature information is determined as the distribution map of houses to be extracted; The house distribution map to be extracted is identified and extracted to obtain the number of houses distributed at the route points; The terrain elevation information of the target route points, the underground pipeline information of the target route points, and the number of houses distributed at the route points are determined as the route optimization extraction data corresponding to the geospatial feature information; The determined data for each route optimization extraction is defined as the route optimization extraction dataset, wherein each data point in the route optimization extraction dataset corresponds to each candidate cable path point identifier in the candidate cable path point identifiers.

3. The method according to claim 1, wherein, The step of generating cable laying information corresponding to the optimized cable line information based on the various geospatial feature information includes: Each geospatial feature information corresponding to each candidate cable route point identifier included in the optimized cable route information is determined as a reference geospatial feature information. For each of the reference geospatial feature information, the soil condition information and contaminated area grid data included in the reference geospatial feature information are determined as cable laying sub-information. The determined cable laying sub-information is used as the cable laying information corresponding to the optimized cable laying information.

4. The method according to claim 1, wherein, The step of generating cable laying method information corresponding to the optimized cable line information based on the cable line laying information includes: The cable laying information is input into a pre-trained cable laying method prediction model to obtain cable laying method information corresponding to the optimized cable laying information.

5. The method according to claim 4, wherein, The cable laying method prediction model is trained through the following steps: Obtain a sample set, wherein the samples in the sample set include sample cable line laying information and sample target cable laying method information corresponding to the sample cable line laying information; Perform the following training steps based on the sample set: The cable laying information of at least one sample in the sample set is input into a preset initial neural network to obtain the sample predicted cable laying method information corresponding to each sample in the at least one sample. The predicted cable laying method information corresponding to each of the at least one samples is compared with the corresponding target cable laying method information. Based on the comparison results, determine whether the preset initial neural network has achieved the preset optimization objective; In response to determining that the preset initial neural network has reached the optimization objective, the preset initial neural network is used as the trained cable laying method prediction model. In response to the determination that the preset initial neural network has not reached the optimization objective, the network parameters of the preset initial neural network are adjusted, and a sample set is formed using unused samples. The adjusted preset initial neural network is then used as the preset initial neural network, and the training steps are executed again.

6. A cable line optimization device based on an artificial intelligence reasoning model, comprising: The first acquisition unit is configured to acquire the identifiers of each candidate cable path point corresponding to a preset cable terminal field identifier group, wherein the preset cable terminal field identifier group includes a cable terminal field start point identifier and a cable terminal field end point identifier, wherein the cable terminal field start point identifier is the identifier of the cable terminal station at the start of the cable line, and the cable terminal field end point identifier is the identifier of the cable terminal station at the end of the cable line. The second acquisition unit is configured to acquire geospatial feature information corresponding to each candidate cable route point identifier from a preset database. Each geospatial feature information includes route point topographic elevation information, route point underground pipeline information, route point soil condition information, route point building distribution map, and contaminated area grid data. The extraction and processing unit is configured to perform route optimization data extraction and processing on the geospatial feature information to obtain a route optimization extraction dataset corresponding to the identifiers of the candidate cable transit points. The third acquisition unit is configured to acquire pre-constructed directed graph data of cable path point identifiers corresponding to the preset cable terminal field identifier group and each candidate cable path point identifier from the preset database. The traversal unit is configured to traverse the directed graph of cable path point identifiers corresponding to the cable path point identifier directed graph data, and obtain the initial cable line information corresponding to the preset cable terminal field identifier group, including: Add the cable terminal field start point identifier in the directed graph of the cable path point identifier to the first preset sequence; The node identifiers corresponding to each direct successor node of the node corresponding to the starting point node of the cable terminal field in the directed graph of the cable path point identifier are determined as the node identifiers of each target candidate cable path point. Based on the identifiers of each target candidate cable route point and the first preset sequence, the following determination steps are performed: For each target candidate cable path point identifier in the various target candidate cable path point identifiers, perform the following steps: In response to determining that the target candidate cable route point identifier is the cable terminal field end point identifier, the target candidate cable route point identifier is added to the first preset sequence to obtain the target first preset sequence; In response to the determination that the target candidate cable route point identifier is not the cable termination field endpoint identifier, the following steps are performed: Add the target candidate cable route point identifier to the first preset sequence to update the first preset sequence; In response to the fact that the candidate cable path point identifiers corresponding to each direct successor node of the node corresponding to the target candidate cable path point identifier in the directed graph of cable path point identifier are not empty, the candidate cable path point identifiers corresponding to each direct successor node of the node corresponding to the target candidate cable path point identifier in the directed graph of cable path point identifier are determined as the target candidate cable path point identifiers, so as to update the target candidate cable path point identifiers. Based on the updated identifiers of each target candidate cable transit point and the updated first preset sequence, the determination step is executed again; Each of the determined targets is first preset sequence and is identified as each of the initial cable line information corresponding to the preset cable terminal field identification group. Each of the initial cable line information includes a cable path point identification sequence, the cable path point identification sequence includes each cable path point identification, and each cable path point identification includes each candidate cable path point identification, cable terminal field start point identification, and cable terminal field end point identification. The optimization processing unit is configured to optimize the initial cable line information based on the line optimization extraction dataset and a pre-trained artificial intelligence inference model to obtain optimized cable line information corresponding to the preset cable terminal field identifier group. The first generation unit is configured to generate cable laying information corresponding to the optimized cable line information based on the various geospatial feature information. The second generation unit is configured to generate cable laying method information corresponding to the optimized cable laying information based on the cable laying information. The display unit is configured to determine the optimized cable line information and the cable laying method information as cable line information, and to display the cable line information on a preset cable line optimization page.

7. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 5.

8. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 5.

Images