Urban operation index decomposition method, terminal device, storage medium and product
Through the target word segmentation model and clustering processing, the problem of low accuracy in obtaining urban operation data by terminal equipment is solved, and automated splitting and accurate data acquisition are realized, reducing time and cost.
Patent Information
- Application Number
- CN202411398720.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-09
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the prior art, the terminal equipment has low accuracy in obtaining urban operation data, and it is time-consuming and cost-effective to manually decompose derived indicators, and there are defects in accuracy and real-time.
The target word segmentation model is used to process word segmentation for dismantling city operation indicators, obtain index name word vectors, and cluster the similarity comparison with the preset standard word vectors to generate an index word vector list to obtain city operation data.
The operation indicators of complex cities can be split without manual calculation, which improves the accuracy of urban operation data obtained by terminal equipment and reduces time and cost.
Smart Images

Figure CN118917989A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a method for decomposing urban operation indicators, a terminal device, a storage medium and a computer program product. Background Art
[0002] With the continuous development of Internet technology, more and more technical personnel will process various benchmark indicator data such as environmental quality, traffic conditions, public safety, and urban planning when conducting urban operation management work in order to obtain the urban operation data they need. However, the relevant benchmark indicator data usually requires the derived indicators to be split before they can be obtained.
[0003] In related technologies, after obtaining derived indicators, technicians need to manually decompose the derived indicators to obtain the indicator names contained in different calculation dimensions, such as business dimension-limited word categories, time dimension-limited word categories, and regional dimension-limited word categories, and then input the extracted indicator names into the terminal device to obtain the city operation data.
[0004] However, the above-mentioned method of manually decomposing each derived indicator usually requires a lot of time, energy and cost for technical personnel, and the indicator information obtained by manual decomposition has certain defects in accuracy and real-time performance, which leads to low accuracy of urban operation data obtained by terminal devices. Summary of the invention
[0005] The main purpose of this application is to provide a method for decomposing urban operation indicators, a terminal device, a storage medium and a computer program product, aiming to solve the technical problem of low accuracy of urban operation data obtained by terminal devices in related technologies.
[0006] To achieve the above purpose, the present application proposes a method for decomposing city operation indicators, which includes: Receive the city operation indicators to be dismantled; Performing word segmentation processing on the city operation index to be disassembled by using a target word segmentation model to determine the word vectors of each indicator name corresponding to the city operation index to be disassembled; Obtain multiple preset standard word vectors, and determine the similarity values between each of the indicator name word vectors and the multiple preset standard word vectors; Based on each of the similarity values, clustering processing is performed on each of the indicator name word vectors to generate a list of each indicator word vector, so as to obtain city operation data according to each of the indicator word vector lists.
[0007] In one embodiment, the step of performing word segmentation processing on the to-be-decomposed city operation indicators through a target word segmentation model to determine the word vectors of each indicator name corresponding to the to-be-decomposed city operation indicators includes: Obtaining a target word segmentation model, and inputting the to-be-decomposed city operation index into the target word segmentation model; Performing word segmentation processing on the to-be-decomposed city operation indicators through the target word segmentation model to determine the names of the city indicators corresponding to the to-be-decomposed city operation indicators; Each of the city indicator names is converted through the target word segmentation model to determine the indicator name word vector corresponding to each of the city indicator names.
[0008] In one embodiment, the step of clustering the indicator name word vectors based on the similarity values to generate a list of indicator word vectors includes: Determining a plurality of preset similarity value ranges; Comparing each of the similarity values with the plurality of preset similarity value ranges respectively to determine a target similarity value range corresponding to each of the similarity values; Determine the target preset standard indicator type corresponding to each of the indicator name word vectors based on the target similarity value range; According to the preset standard indicator type of each target, the word vectors of each indicator name are clustered to generate a list of word vectors for each indicator.
[0009] In one embodiment, the step of determining the target preset standard indicator type corresponding to each of the indicator name word vectors based on the target similarity value ranges includes: Determine a plurality of preset standard word vectors, and preset standard indicator types corresponding to each of the plurality of preset standard word vectors; Based on the target similarity value ranges, determining the target preset standard word vectors corresponding to the indicator name word vectors; Based on each of the target preset standard word vectors, determine the target preset standard indicator type corresponding to each of the indicator name word vectors.
[0010] In one embodiment, after the step of receiving the city operation index to be disassembled, the method further includes: Identifying the city operation indicator to be disassembled to determine whether the city operation indicator to be disassembled is a derived indicator; If it is determined that the city operation indicator to be disassembled is not a derived indicator, obtaining preset non-derived identification information, and generating non-derived indicator prompt information based on the non-derived identification information and the city operation indicator to be disassembled; The non-derived indicator prompt information is sent to a data source terminal, wherein the data source terminal is a terminal device that generates the city operation indicator to be disassembled.
[0011] In one embodiment, before the step of receiving the city operation index to be disassembled, the method includes: Get the initial word segmentation model; Determine a plurality of preset standard indicator names, and preset standard word vectors corresponding to the plurality of preset standard indicator names; The initial word segmentation model is trained based on multiple preset standard indicator names and multiple preset standard word vectors to generate a target word segmentation model.
[0012] In one embodiment, the step of training the initial word segmentation model based on the plurality of preset standard indicator names and the plurality of preset standard word vectors to generate a target word segmentation model includes: Inputting a plurality of the preset standard indicator names into the initial word segmentation model, and determining a word vector to be verified output by the initial word segmentation model, wherein the word vector to be verified is a word vector generated by the initial word segmentation model based on the preset standard indicator name; Determining the word segmentation success rate of the initial word segmentation model based on each of the verification word vectors and the plurality of preset standard word vectors; When it is detected that the word segmentation success rate reaches a preset success rate threshold, the initial word segmentation model is determined as a target word segmentation model.
[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a terminal device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the method for decomposing urban operation indicators as described above.
[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for decomposing urban operation indicators as described above are implemented.
[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the method for decomposing urban operation indicators as described above.
[0016] The method for decomposing urban operation indicators provided in the embodiment of the present application comprises the following steps: receiving the urban operation indicators to be decomposed; receiving the urban operation indicators to be decomposed; performing word segmentation processing on the urban operation indicators to be decomposed through a target word segmentation model to determine each indicator name word vector corresponding to the urban operation indicators to be decomposed; obtaining a plurality of preset standard word vectors, and determining each similarity value between each of the indicator name word vectors and a plurality of the preset standard word vectors; performing clustering processing on each of the indicator name word vectors based on each of the similarity values to generate a list of each indicator word vector, so as to obtain urban operation data according to each of the indicator word vector lists.
[0017] In this embodiment, when the terminal device is running, it first receives the city operation indicators to be disassembled sent by the data source terminal, and then the terminal device inputs the obtained city operation indicators to be disassembled into the target word segmentation model, so that the target word segmentation model performs word segmentation processing on the city operation indicators to be disassembled, so as to determine the indicator name word vectors corresponding to the city operation indicators to be disassembled, and then the terminal device obtains multiple preset standard word vectors, and compares each indicator name word vector with multiple preset standard word vectors respectively, so as to determine the similarity value generated between each indicator name word vector and multiple preset standard word vectors, and finally, the terminal device clusters each indicator name word vector based on each similarity value, so as to generate an indicator word vector list containing indicator name word vectors of the same type, and then performs data analysis operations according to each indicator word vector list to obtain each city operation data.
[0018] In this way, the present application solves the technical problem of low accuracy of urban operation data obtained by terminal devices in the related technology. That is, the present application calls the target word segmentation model to split the urban operation indicators to be split to obtain the word vectors of each indicator name corresponding to the urban operation indicators to be split, and then clusters the word vectors of each indicator name to obtain a plurality of indicator word vector lists containing the same type of indicator name word vectors. Without manual calculation, technical personnel can split complex urban operation indicators to obtain the indicator names contained in different calculation dimensions, thereby enabling the terminal device to obtain accurate urban operation data. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0021] Figure 1 A flow chart of the first embodiment of the method for decomposing the city operation index of the present application; Figure 2 A detailed flow chart of an embodiment of a method for decomposing city operation indicators of the present application; Figure 3 A flow chart of the second embodiment of the method for decomposing the city operation index of the present application; Figure 4 This is a schematic diagram of the model training process involved in Example 2 of the method for decomposing urban operation indicators of this application; Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the method for decomposing urban operation indicators in the embodiment of the present application.
[0022] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0023] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0024] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0025] In this embodiment, for ease of description, the following description will be based on a terminal device that is internally configured with a model training module and a storage module and can communicate with a preset urban operation standard indicator library, or a mobile terminal, data storage control terminal, PC or other terminal connected to an electronic control unit configured on the terminal device as the execution entity.
[0026] Based on the above-mentioned terminal equipment, the overall concept of the decomposition method of the city operation index of this application is proposed here.
[0027] With the continuous development of Internet technology, more and more technicians will use the method of processing various benchmark indicator data such as environmental quality, traffic conditions, public safety, and urban planning when conducting urban operation management work to obtain the urban operation data they need. However, the relevant benchmark indicator data usually needs to be split after the derived indicators are obtained. In the related technology, after obtaining the derived indicators, the technicians need to manually decompose the derived indicators to obtain the indicator names contained in different calculation dimensions such as business dimension limiting word classes, time dimension limiting word classes, and regional dimension limiting word classes, and then input the extracted indicator names into the terminal device to obtain the urban operation data. However, the above-mentioned method of manually decomposing each derived indicator usually requires a lot of time, energy and cost for the technicians, and the indicator information obtained by manual decomposition has certain defects in accuracy and real-time performance, which leads to the low accuracy of the urban operation data obtained by the terminal device.
[0028] In response to the above phenomenon, the present application provides a method for decomposing urban operation indicators, which includes: receiving urban operation indicators to be decomposed; performing word segmentation processing on the urban operation indicators to be decomposed through a target word segmentation model to determine each indicator name word vector corresponding to the urban operation indicators to be decomposed; obtaining multiple preset standard word vectors, and determining each similarity value between each of the indicator name word vectors and the multiple preset standard word vectors; clustering each of the indicator name word vectors based on the similarity values to generate a list of each indicator word vector, so as to obtain urban operation data according to each list of indicator word vectors.
[0029] In this way, the present application solves the technical problem of low accuracy of urban operation data obtained by terminal devices in the related technology. That is, the present application calls the target word segmentation model to split the urban operation indicators to be split to obtain the word vectors of each indicator name corresponding to the urban operation indicators to be split, and then clusters the word vectors of each indicator name to obtain a plurality of indicator word vector lists containing the same type of indicator name word vectors. Without manual calculation, technical personnel can split complex urban operation indicators to obtain the indicator names contained in different calculation dimensions, thereby enabling the terminal device to obtain accurate urban operation data.
[0030] Based on the overall concept of the method for decomposing the city operation index of the present application, the embodiment of the present application provides a method for decomposing the city operation index, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for decomposing urban operation indicators of the present application.
[0031] In this embodiment, the method for decomposing the city operation index of the present application includes steps S10 to S40: Step S10: receiving the city operation index to be disassembled; Step S20: performing word segmentation processing on the city operation index to be disassembled by using a target word segmentation model to determine word vectors of each indicator name corresponding to the city operation index to be disassembled; It should be noted that the city operation index is the relevant indicator data used for city planning and operation management. The city operation index specifically includes benchmark indicators and derived indicators. The benchmark indicator is an indicator that can be calculated and processed separately, including but not limited to: housing, area, transaction, traffic congestion level, air quality, etc. In addition, the derived indicator is a statistical indicator obtained by adding statistical granularity to the benchmark indicator. It can be understood that the statistical granularity can specifically be a time dimension, a regional dimension, a business dimension, etc.
[0032] In this embodiment, when the terminal device is running, it first receives the city operation indicators to be disassembled sent by the data source terminal for city planning and operation management. After that, the terminal device inputs the city operation indicators to be disassembled into the target word segmentation model configured by itself, so that the target word segmentation model performs word segmentation processing on the city operation indicators to be disassembled to extract the word vectors of each indicator name corresponding to the city operation indicators to be disassembled.
[0033] For example, see Figure 2 , Figure 2 This is a detailed flow chart of an embodiment of the method for decomposing city operation indicators of the present application, such as Figure 2 As shown, when the terminal device is running, it first obtains the city operation indicator to be disassembled "the reading transaction area of commercial housing in Longhua District, Shenzhen City" sent by the urban management terminal. After that, the terminal device reads the model training module configured by itself, thereby obtaining the target BERT Chinese pre-training model trained by the model training module. The terminal device then inputs the city operation indicator to be disassembled into the target BERT Chinese pre-training model, and the target BERT Chinese pre-training model disassembles the city operation indicator to be disassembled "the reading transaction area of commercial housing in Longhua District, Shenzhen City", so as to obtain the indicator name word vectors corresponding to the city operation indicator to be disassembled, which are "Shenzhen City [word vector]", "Longhua District [word vector]", "Commodity [word vector]", "Housing [word vector]", "Monthly [word vector]", and "Area [word vector]".
[0034] In a feasible implementation manner, the above step S20 may specifically include steps S201 to S203: Step S201: obtaining a target word segmentation model, and inputting the to-be-decomposed city operation index into the target word segmentation model; Step S202: performing word segmentation processing on the city operation index to be disassembled by using the target word segmentation model to determine the names of the city indicators corresponding to the city operation index to be disassembled; Step S203: converting each of the city indicator names through the target word segmentation model to determine the indicator name word vector corresponding to each of the city indicator names.
[0035] In this embodiment, after obtaining the city operation indicators to be disassembled, the terminal device first reads the model training module configured by itself, thereby obtaining the target word segmentation model trained by the model training module. After that, the terminal device inputs the obtained city operation indicators to be disassembled into the target word segmentation model, and the target word segmentation model performs word segmentation processing on the city operation indicators to be disassembled, thereby extracting the names of each city indicator contained in the city operation indicators to be disassembled. Finally, the target word segmentation model converts the name of each city indicator, thereby obtaining the indicator name word vector corresponding to each city indicator name.
[0036] For example, for example, Figure 2As shown, after the terminal device obtains the city operation indicator to be disassembled "the reading transaction area of commercial housing in Longhua District, Shenzhen City", the terminal device first reads the model training module configured by itself to obtain the target BERT Chinese pre-training model trained by the model training module. After that, the terminal device inputs the city operation indicator to be disassembled into the target BERT Chinese pre-training model, so that the target BERT Chinese pre-training model performs word segmentation processing on the city operation indicator to be disassembled, so as to determine that the names of the city indicators contained in the city operation indicator to be disassembled "the reading transaction area of commercial housing in Longhua District, Shenzhen City" are "Shenzhen City", "Longhua District", "Commodity", "Housing", "Monthly", "Transaction", and "Area". Finally, the target BERT Chinese pre-training model converts the city indicator name "Shenzhen City", so as to determine that the indicator name word vector corresponding to the city indicator name "Shenzhen City" is "Shenzhen City [Word Vector]", and at the same time, the target BERT Chinese pre-training model converts the city indicator name "Longhua District", so as to determine that the city indicator name "Longhua District" The corresponding indicator name word vector is "Longhua District [word vector]". At the same time, the target BERT Chinese pre-training model converts the city indicator name "commodity", thereby determining that the indicator name word vector corresponding to the city indicator name "commodity" is "commodity [word vector]". At the same time, the target BERT Chinese pre-training model converts the city indicator name "housing", thereby determining that the indicator name word vector corresponding to the city indicator name "housing" is "housing [word vector]". At the same time, the target BERT Chinese pre-training model converts the city indicator name "monthly", thereby determining that the indicator name word vector corresponding to the city indicator name "monthly" is "monthly [word vector]". At the same time, the target BERT Chinese pre-training model converts the city indicator name "transaction", thereby determining that the indicator name word vector corresponding to the city indicator name "transaction" is "transaction [word vector]". At the same time, the target BERT Chinese pre-training model converts the city indicator name "area", thereby determining that the indicator name word vector corresponding to the city indicator name "area" is "area [word vector].
[0037] Step S30: obtaining a plurality of preset standard word vectors, and determining the similarity values between each of the indicator name word vectors and the plurality of preset standard word vectors; It should be noted that the preset standard word vector is a word vector corresponding to each preset standard indicator name for city planning and operation management contained in the city operation standard indicator library. It can be understood that the city operation standard indicator library contains each of the above-mentioned benchmark indicators and each of the above-mentioned derived indicators. At the same time, the city operation standard indicator library also contains the preset standard indicator type, preset standard indicator name and preset standard word vector corresponding to each benchmark indicator and each derived indicator. It can be understood that there are many ways to construct the city operation standard indicator library, and this application does not limit this.
[0038] In this embodiment, after determining the word vector of each indicator name, the terminal device further accesses the city operation standard indicator library that is communicated with itself, thereby obtaining multiple preset standard word vectors contained in the city operation standard indicator library. The terminal device then compares each indicator name word vector with the multiple preset standard word vectors respectively, thereby determining each indicator name word vector, and the similarity values generated between each of the multiple preset standard word vectors.
[0039] For example, for example, Figure 2 As shown, after determining the word vectors of each indicator name "Shenzhen City [word vector]", "Longhua District [word vector]", "Commodity [word vector]", "Housing [word vector]", "Monthly [word vector]", "Transaction [word vector]", and "Area [word vector]", the terminal device further accesses the urban operation standard indicator library that is connected to itself for communication, and determines the preset standard word vectors contained in the urban operation standard indicator library. The terminal device then compares "Shenzhen City [word vector]", "Longhua District [word vector]", "Commodity [word vector]", "Housing [word vector]", "Monthly [word vector]", "Transaction [word vector]", and "Area [word vector]" with each of the multiple preset standard word vectors, thereby determining the cosine similarity between "Shenzhen City [word vector]", "Longhua District [word vector]", "Commodity [word vector]", "Housing [word vector]", "Monthly [word vector]", "Transaction [word vector]", and "Area [word vector]" and each of the multiple preset standard word vectors.
[0040] It should be noted that the specific calculation process of comparing the indicator name word vector with the preset standard word vector to determine the cosine similarity between the indicator name word vector and the preset standard word vector is prior art, so it will not be repeated here.
[0041] Step S40: clustering the indicator name word vectors based on the similarity values to generate a list of indicator word vectors, so as to obtain city operation data according to the list of indicator word vectors.
[0042] In this embodiment, after obtaining the similarity values corresponding to each indicator name word vector, the terminal device further performs clustering processing on each indicator name word vector based on each similarity value, thereby combining indicator name word vectors of the same type to generate multiple indicator word vector lists containing indicator name word vectors of the same type. The terminal device then determines the city operation data corresponding to the city operation indicators to be disassembled based on each indicator word vector list.
[0043] For example, for example, Figure 2As shown, after obtaining the cosine similarities corresponding to "Shenzhen City [word vector]", "Longhua District [word vector]", "Commodity [word vector]", "Housing [word vector]", "Monthly [word vector]", "Transaction [word vector]", and "Area [word vector]", the terminal device further determines the target preset standard indicator type corresponding to each indicator name word vector according to each cosine similarity, and performs clustering processing according to each target preset standard indicator type to determine that "Commodity [word vector]" is a business dimension-limited word class, and determines that "Shenzhen City [word vector]" and "Longhua District [word vector]" are regional dimension-limited word classes, and determines that "Monthly [word vector]" is a time dimension-limited word class, and determines that "Housing [word vector]", "Transaction [word vector]", "Area [word vector]" is the word class of the benchmark indicator name. The terminal device then generates a business qualifier field list based on the business dimension qualifier word class, generates a regional dimension field list based on the regional dimension qualifier word class, generates a time dimension field list based on the time dimension qualifier word class, and generates a benchmark indicator name field list based on the benchmark indicator name word class. The terminal device then obtains the city operation data that matches the above-mentioned city operation indicators to be disassembled based on the business qualifier field list, the regional dimension field list, the time dimension field list, and the benchmark indicator name field list. At the same time, the terminal device can also update the above-mentioned city operation standard indicator library based on the business qualifier field list, the regional dimension field list, the time dimension field list, and the benchmark indicator name field list.
[0044] In a feasible implementation manner, the above step S40 may specifically include steps S401 to S404: Step S401: determining a plurality of preset similarity value ranges; Step S402: comparing each of the similarity values with a plurality of the preset similarity value ranges respectively, to determine a target similarity value range corresponding to each of the similarity values; Step S403: determining the target preset standard indicator type corresponding to each of the indicator name word vectors based on the target similarity value range; Step S404: According to the preset standard indicator types of each target, cluster the word vectors of each indicator name to generate a list of each indicator word vector.
[0045] In this embodiment, after obtaining each similarity value corresponding to each indicator name word vector, the terminal device first reads the storage module configured by itself to obtain multiple preset similarity value ranges. Then, the terminal device compares each similarity value obtained with the multiple preset similarity value ranges, thereby determining the multiple target similarity value ranges in which each similarity value is located. Then, based on each target similarity value range, the terminal device determines the target preset standard indicator type corresponding to each indicator name word vector in the urban operation standard indicator library. Finally, the terminal device clusters each indicator name word vector according to the target preset standard indicator type corresponding to each indicator name word vector, so as to generate an indicator word vector list based on the indicator name word vectors of the same indicator type.
[0046] For example, for example, Figure 2 As shown, after obtaining the cosine similarities corresponding to "Shenzhen City [word vector]", "Longhua District [word vector]", "Commodity [word vector]", "Housing [word vector]", "Monthly [word vector]", "Transaction [word vector]", and "Area [word vector]", the terminal device first reads the storage module configured by itself to obtain multiple preset similarity value ranges. After that, the terminal device compares each cosine similarity with each preset similarity value range, thereby determining multiple target similarity value ranges corresponding to each indicator name word vector. After that, the terminal device determines whether the indicator name word vector and each preset standard word vector are similar based on the multiple target similarity value ranges, thereby determining "Shenzhen City [word vector]" as the regional dimension limited word class based on each judgment result and determining "Longhua District [word vector]" as the regional dimension limited word class. The district dimension limits the word class, determines that "commodity [word vector]" is the business dimension limiting word class, determines that "housing [word vector]", "transaction [word vector]", and "area [word vector]" are all benchmark indicator name word classes, and determines that "monthly [word vector]" is the time dimension limiting word class. Finally, the terminal device clusters "commodity [word vector]" according to the business dimension limiting word class to generate a business limiting word field list, and clusters "Shenzhen City [word vector]" and "Longhua District [word vector]" according to the district dimension limiting word class to generate a district dimension field list, and clusters "housing [word vector] "transaction [word vector]", "area [word vector]" according to the benchmark indicator name word class to generate a benchmark indicator name field list, and clusters "monthly [word vector]" according to the time dimension limiting word class to generate a time dimension field list.
[0047] In a feasible implementation manner, the above step S403 may specifically include steps S4031 to S4033: Step S4031: determining a plurality of preset standard word vectors and preset standard indicator types corresponding to the plurality of preset standard word vectors; Step S4032: determining the target preset standard word vector corresponding to each of the indicator name word vectors based on the target similarity value ranges; Step S4033: Based on each of the target preset standard word vectors, determine the target preset standard indicator type corresponding to each of the indicator name word vectors.
[0048] In this embodiment, after determining the target similarity value range corresponding to each indicator name word vector, the terminal device first accesses the above-mentioned urban operation standard indicator library to determine the multiple preset standard word vectors contained in the urban operation standard indicator library, and determines the preset standard indicator type corresponding to each of the multiple preset standard word vectors. Afterwards, the terminal device determines whether each indicator name word vector is similar to each preset standard word vector based on each target similarity value range, thereby determining the target preset standard word vector that matches each indicator name word vector in each preset standard word vector. Finally, the terminal device determines the preset standard indicator type corresponding to each target preset standard word vector as the target preset standard indicator type corresponding to each indicator name word vector.
[0049] For example, for example, Figure 2 As shown, after determining the target similarity value range corresponding to each indicator name word vector, the terminal device first accesses the above-mentioned city operation standard indicator library, thereby determining multiple preset standard word vectors contained in the city operation standard indicator library, and determining the preset standard indicator names corresponding to each of the multiple preset standard word vectors. The terminal device then determines the preset standard indicator type corresponding to each preset standard indicator name. After that, if the terminal device determines that the cosine similarity between "Shenzhen City [word vector]" and multiple preset standard area name word vectors contained in the city operation standard indicator library is within the preset high similarity value range, and determines that the cosine similarity between "Shenzhen City [word vector]" and multiple preset standard business name word vectors and multiple preset standard time name word vectors contained in the city operation standard indicator library is within the preset low similarity value range, then the terminal device determines that each preset standard area name word vector contained in the city operation standard indicator library is the target preset indicator word vector corresponding to the indicator name word vector "Shenzhen City [word vector]". Finally, the terminal device determines that the regional dimension limiting word class corresponding to each preset standard area name word vector is the target preset standard indicator type corresponding to the indicator name word vector; Similarly, the terminal device repeats the above steps to determine that the target preset standard indicator type corresponding to "Longhua District [word vector]" is a regional dimension-restricted word class, and determines that the target preset standard indicator type corresponding to "commodity [word vector]" is a business dimension-restricted word class, and determines that "monthly [word vector]" is a time dimension-restricted word class; At the same time, when the terminal device determines that the cosine similarities between "transaction [word vector]", "area [word vector]", and "housing [word vector]" and each preset standard word vector are in the preset low similarity value range, it determines that "transaction [word vector]", "area [word vector]", and "housing [word vector]" are not any of the regional dimension-limited word classes, business dimension-limited word classes, and time dimension-limited word classes, and further determines that "transaction [word vector]", "area [word vector]", and "housing [word vector]" are all benchmark indicator name word classes.
[0050] In addition, in this embodiment and another embodiment, after determining each similarity value, the terminal device can also obtain a preset similarity threshold, and compare each similarity value with each similarity threshold to obtain a comparison result. Afterwards, if the terminal device detects that the cosine similarity between any indicator name word vector and the above-mentioned preset standard word vectors does not reach the similarity threshold, it determines that the abnormal indicator name word vector is other class name word class, and thus discards the abnormal indicator name word vector.
[0051] In this embodiment, when the terminal device is running, it first receives the city operation indicators to be disassembled for planning and operation management of the city sent by the data source terminal. Then, the terminal device inputs the city operation indicators to be disassembled into the target word segmentation model configured by itself, so that the target word segmentation model performs word segmentation processing on the city operation indicators to be disassembled, so as to extract the name word vectors of each indicator corresponding to the city operation indicators to be disassembled. Then, the terminal device accesses the city operation standard indicator library connected to itself by communication, so as to obtain multiple preset standard word vectors contained in the city operation standard indicator library, and the terminal device then compares each indicator name word vector with the multiple preset standard word vectors respectively, so as to determine the similarity values generated between each indicator name word vector and the multiple preset standard word vectors respectively. Finally, the terminal device performs clustering processing on each indicator name word vector based on each similarity value, so as to combine the indicator name word vectors of the same type to generate multiple indicator word vector lists containing the indicator name word vectors of the same type, and the terminal device then determines the city operation data corresponding to the city operation indicators to be disassembled according to each indicator word vector list.
[0052] In this way, the present application solves the technical problem of low accuracy of urban operation data obtained by terminal devices in the related technology. That is, the present application calls the target word segmentation model to split the urban operation indicators to be split to obtain the word vectors of each indicator name corresponding to the urban operation indicators to be split, and then clusters the word vectors of each indicator name to obtain a plurality of indicator word vector lists containing the same type of indicator name word vectors. Without manual calculation, technical personnel can split complex urban operation indicators to obtain the indicator names contained in different calculation dimensions, thereby enabling the terminal device to obtain accurate urban operation data.
[0053] Based on the first embodiment of the present application, a second embodiment of the present application is proposed. In the second embodiment of the present application, the same or similar contents as those of the first embodiment can be referred to the above description and will not be described in detail later. On this basis, after the above step S10, the decomposition method of the city operation index of the present application can also include steps A10 to A30: Step A10: Identifying the city operation index to be disassembled to determine whether the city operation index to be disassembled is a derived index; Step A20: if it is determined that the city operation index to be disassembled is not a derived index, obtaining preset non-derived identification information, and generating non-derived indicator prompt information based on the non-derived identification information and the city operation index to be disassembled; Step A30: Send the non-derived indicator prompt information to a data source terminal, wherein the data source terminal is a terminal device that generates the city operation indicator to be disassembled.
[0054] In this embodiment, after receiving the city operation indicator to be disassembled, the terminal device first identifies the city operation indicator to be disassembled, so as to determine whether the city operation indicator to be disassembled is a derived indicator. Then, if the terminal device determines that the city operation indicator to be disassembled is not a derived indicator, the terminal device reads the above-mentioned storage module to obtain the preset non-derived identification information, and the terminal device then adds the non-derived identification information to the city operation indicator to be disassembled to generate non-derived indicator prompt information. Finally, the terminal device outputs the non-derived indicator prompt information to the above-mentioned data source terminal that sends the disassembled city operation indicator to the terminal device, so as to stop disassembling the disassembled city operation indicator.
[0055] Exemplarily, for example, after receiving the city operation indicator to be disassembled, the terminal device first reads the city operation indicator to be disassembled, and then determines whether the city operation indicator to be disassembled is a derived indicator based on whether the city operation indicator to be disassembled contains a derived identifier. Afterwards, if the terminal device identifies that the city operation indicator to be disassembled does not contain a derived indicator, it determines that the city operation indicator to be disassembled is a non-derived indicator. The terminal device then reads the storage module configured by itself to obtain the preset non-derived identification information, and adds the non-derived identification information to the city operation indicator to be disassembled to generate a non-derived indicator prompt information. Finally, the terminal device then accesses the city management terminal that sent the city operation indicator to be disassembled, and then transmits the non-derived indicator prompt information back to the city management terminal to complete the disassembly work of the city operation indicator to be disassembled.
[0056] In this way, the terminal device can identify the acquired city operation indicators to be disassembled, and when it is identified that the city operation indicators to be disassembled are non-derived indicators, the disassembly work of the city operation indicators to be disassembled can be stopped in time, thereby further improving the data processing efficiency of the terminal device.
[0057] Based on the first embodiment and / or the second embodiment of the present application, the third embodiment of the present application is proposed here. In the third embodiment of the present application, the same or similar contents as those of the above embodiments can be referred to the above introduction and will not be described in detail later. Figure 3 , Figure 3 The flowchart provided in Example 2 of the method for decomposing the city operation index of this application is as follows: Figure 3 As shown, before the above step S10, the method for decomposing the city operation index of the present application may further include steps B10 to B30: Step B10: Obtaining an initial word segmentation model; Step B20: determining a plurality of preset standard indicator names and preset standard word vectors corresponding to the plurality of preset standard indicator names; Step B30: Training the initial word segmentation model based on the plurality of preset standard indicator names and the plurality of preset standard word vectors to generate a target word segmentation model.
[0058] In this embodiment, before receiving the city operation indicators to be disassembled, the terminal device first reads the model training module configured by itself, so as to determine the initial word segmentation model installed in the model training module. After that, the terminal device accesses the city operation standard instruction library that is connected to itself for communication, so as to obtain multiple preset standard indicator names contained in the city operation standard instruction library, and the preset standard word vectors corresponding to each of the multiple preset standard indicator names. Finally, the terminal device inputs the obtained multiple preset standard indicator names into the model training module, and the model training module trains the initial word segmentation model based on the multiple preset standard indicator names and the multiple preset standard word vectors to generate a target word segmentation model that can accurately segment the city operation indicators.
[0059] Exemplarily, for example, before receiving the above-mentioned city operation indicators to be disassembled sent by the city management system, the terminal device first reads the model training module configured by itself, so as to determine the initial BERT Chinese pre-training model installed in the model training module. After that, the terminal device accesses the city operation standard instruction library that is connected to itself for communication, so as to determine the multiple preset standard instruction names contained in the city operation standard instruction library, and determines the preset standard word vectors corresponding to each of the multiple preset standard instruction names in the city operation standard instruction library. Finally, the terminal device inputs each preset standard instruction name and each preset standard word vector into the model training module, and the model training module inputs each preset standard instruction name into the initial BERT Chinese pre-training model, and verifies the word vectors to be screened output by the initial BERT Chinese pre-training model based on each preset standard word vector, so as to adjust the initial BERT Chinese pre-training model based on the verification result to obtain the target BERT Chinese pre-training model that can accurately segment words.
[0060] In this way, the terminal device can train the preset initial BERT Chinese pre-training model through the city operation standard instruction library, thereby obtaining the target BERT Chinese pre-training model that can perform accurate word segmentation operations.
[0061] In a feasible implementation manner, the above step B30 may specifically include steps B301 to B303: Step B301: inputting a plurality of the preset standard indicator names into the initial word segmentation model, and determining a word vector to be verified output by the initial word segmentation model, wherein the word vector to be verified is a word vector generated by the initial word segmentation model based on the preset standard indicator name; Step B302: determining the word segmentation success rate of the initial word segmentation model based on each of the verification word vectors and a plurality of the preset standard word vectors; Step B303: when it is detected that the word segmentation success rate reaches a preset success rate threshold, the initial word segmentation model is determined as a target word segmentation model.
[0062] In this embodiment, after obtaining multiple preset standard indicators and multiple preset standard word vectors, the terminal device first inputs the multiple preset standard indicator names and the multiple preset standard word vectors into the model training module, so that the model training module inputs the multiple preset standard indicator names into the initial word segmentation model, and then the initial word segmentation model performs word segmentation processing on the multiple preset standard indicator names, thereby generating multiple word vectors to be verified. After that, the model training module determines to compare the multiple word vectors to be verified with their respective corresponding preset standard word vectors, so as to determine the word segmentation success rate corresponding to the initial word segmentation model. Finally, the model training module obtains a preset success rate threshold, and when it is determined that the word segmentation success rate reaches the success rate threshold, the initial word segmentation model is determined as the target word segmentation model. Similarly, when the model training module determines that the success rate does not reach the success rate threshold, the initial word segmentation model is fine-tuned, and when it is determined that the word segmentation success rate of the adjusted initial word segmentation model reaches the success rate threshold, the adjusted initial word segmentation model is determined as the target word segmentation model.
[0063] For example, see Figure 4 , Figure 4 This is a schematic diagram of the model training process involved in the second embodiment of the method for decomposing urban operation indicators of this application, such as Figure 4As shown, after obtaining multiple preset standard indicators and multiple preset standard word vectors, the terminal device first inputs the multiple preset standard indicator names and the multiple preset standard word vectors into the model training module, so that the model training module inputs the multiple preset standard indicator names into the preset initial BERT Chinese pre-training model, and then the initial BERT Chinese pre-training model performs word segmentation processing on the input multiple preset standard indicator names to output the to-be-screened word vectors corresponding to each of the multiple preset standard indicator names. After that, the model training module determines the preset standard word vectors corresponding to each of the multiple preset standard indicator names, and compares the to-be-screened word vectors corresponding to each of the multiple preset standard indicator names with the preset standard word vectors corresponding to each of the multiple preset standard indicator names. Then, when it is determined that the to-be-screened word vector is consistent with the corresponding preset standard word vector, it is determined that the word segmentation is successful. The terminal device then determines the word segmentation success rate corresponding to the initial BERT Chinese pre-training model based on each to-be-screened word vector and each preset standard word vector. After that, the model training module obtains the preset success rate threshold, and compares the word segmentation success rate with the preset success rate threshold. When the model training module determines that the word segmentation success rate reaches the preset success rate threshold, it determines that the initial BERT Chinese pre-training model can accurately segment the indicator name, thereby determining the initial BERT Chinese pre-training model as the target BERT Chinese pre-training model that can segment the city operation indicators to be screened. Similarly, if the model training module determines that the word segmentation success rate does not reach the preset success rate threshold, it determines that the initial BERT Chinese pre-training model cannot segment the indicator name, thereby adjusting the initial BERT Chinese pre-training model, and re-identifying each preset standard indicator name based on the adjusted initial BERT Chinese pre-training model, and then when it is determined that the word segmentation success rate of the adjusted initial BERT Chinese pre-training model reaches the preset success rate threshold, the adjusted initial BERT Chinese pre-training model is determined to be the target BERT Chinese pre-training model.
[0064] It is understandable that the specific process of adjusting the BERT Chinese pre-training model based on the model training module is an existing technology, so it will not be repeated here. In this way, the terminal device can train the preset initial BERT Chinese pre-training model through the city operation standard instruction library, thereby obtaining a target BERT Chinese pre-training model that can perform accurate word segmentation operations.
[0065] The present application provides a terminal device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for decomposing urban operation indicators in the above-mentioned embodiment one.
[0066] Reference below Figure 5 , which shows a schematic diagram of the structure of a terminal device suitable for implementing the embodiment of the present application. The terminal device in the embodiment of the present application may include, but is not limited to, a terminal device that is internally configured with a model training module and a storage module and can communicate with a preset urban operation standard indicator library, or a mobile terminal, a data storage control terminal, a PC, etc. connected to an electronic control unit configured on the terminal device. Figure 5 The terminal device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0067] like Figure 5 As shown, the terminal device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the terminal device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the terminal device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a terminal device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.
[0068] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0069] The terminal device provided by the present application adopts the method for decomposing the city operation index in the above embodiment, which can solve the technical problem of low accuracy of the city operation data obtained by the terminal device in the related technology. Compared with the prior art, the beneficial effects of the terminal device provided by the present application are the same as the beneficial effects of the method for decomposing the city operation index provided by the above embodiment, and the other technical features in the terminal device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0070] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0071] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0072] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the method for decomposing urban operation indicators in the above-mentioned embodiment.
[0073] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.
[0074] The computer-readable storage medium may be included in the terminal device; or may exist independently without being installed in the terminal device.
[0075] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the terminal device, the terminal device: receives the city operation indicators to be disassembled, performs word segmentation processing on the city operation indicators to be disassembled through the target word segmentation model to determine the word vectors of each indicator name corresponding to the city operation indicators to be disassembled; obtains multiple preset standard word vectors, and determines the similarity values between each of the indicator name word vectors and the multiple preset standard word vectors; clusters the indicator name word vectors based on the similarity values to generate a list of indicator word vectors, so as to obtain city operation data according to the list of indicator word vectors.
[0076] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0077] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0078] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0079] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for decomposing the city operation index, and can solve the technical problem of low accuracy of the city operation data obtained by the terminal device in the related art. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the method for decomposing the city operation index provided by the above-mentioned embodiment, and will not be elaborated here.
[0080] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned method for decomposing urban operation indicators when executed by a processor.
[0081] The computer program product provided by this application can solve the technical problem of low accuracy of urban operation data obtained by terminal devices in the related art. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the decomposition method of urban operation indicators provided by the above embodiment, which will not be repeated here.
[0082] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A method for decomposing urban operation indicators, characterized in that: The decomposition method of the urban operation index includes: Receive the city operation indicators to be dismantled; Performing word segmentation processing on the city operation index to be disassembled by using a target word segmentation model to determine the word vectors of each indicator name corresponding to the city operation index to be disassembled; Obtain multiple preset standard word vectors, and determine the similarity values between each of the indicator name word vectors and the multiple preset standard word vectors; Based on each of the similarity values, clustering processing is performed on each of the indicator name word vectors to generate a list of each indicator word vector, so as to obtain city operation data according to each of the indicator word vector lists.
2. The method for decomposing urban operation indicators according to claim 1, characterized in that: The step of performing word segmentation processing on the to-be-decomposed city operation indicators through the target word segmentation model to determine the word vectors of each indicator name corresponding to the to-be-decomposed city operation indicators includes: Obtaining a target word segmentation model, and inputting the to-be-decomposed city operation index into the target word segmentation model; Performing word segmentation processing on the to-be-decomposed city operation indicators through the target word segmentation model to determine the names of the city indicators corresponding to the to-be-decomposed city operation indicators; Each of the city indicator names is converted through the target word segmentation model to determine the indicator name word vector corresponding to each of the city indicator names.
3. The method for decomposing urban operation indicators according to claim 2, characterized in that: The step of clustering the indicator name word vectors based on the similarity values to generate a list of indicator word vectors includes: Determining a plurality of preset similarity value ranges; Comparing each of the similarity values with the plurality of preset similarity value ranges respectively to determine a target similarity value range corresponding to each of the similarity values; Determine the target preset standard indicator type corresponding to each of the indicator name word vectors based on the target similarity value range; According to the preset standard indicator type of each target, the word vectors of each indicator name are clustered to generate a list of word vectors for each indicator.
4. The method for decomposing urban operation indicators according to claim 3, characterized in that: The step of determining the target preset standard indicator type corresponding to each of the indicator name word vectors based on the target similarity value ranges includes: Determine a plurality of preset standard word vectors, and preset standard indicator types corresponding to each of the plurality of preset standard word vectors; Based on the target similarity value ranges, determining the target preset standard word vectors corresponding to the indicator name word vectors; Based on each of the target preset standard word vectors, determine the target preset standard indicator type corresponding to each of the indicator name word vectors.
5. The method for decomposing urban operation indicators according to claim 1, characterized in that: After the step of receiving the city operation index to be disassembled, the method further includes: Identifying the city operation indicator to be disassembled to determine whether the city operation indicator to be disassembled is a derived indicator; If it is determined that the city operation indicator to be disassembled is not a derived indicator, obtaining preset non-derived identification information, and generating non-derived indicator prompt information based on the non-derived identification information and the city operation indicator to be disassembled; The non-derived indicator prompt information is sent to a data source terminal, wherein the data source terminal is a terminal device that generates the city operation indicator to be disassembled.
6. The method for decomposing urban operation indicators according to any one of claims 1 to 5, characterized in that: Before the step of receiving the city operation index to be disassembled, the method includes: Get the initial word segmentation model; Determine a plurality of preset standard indicator names, and preset standard word vectors corresponding to the plurality of preset standard indicator names; The initial word segmentation model is trained based on multiple preset standard indicator names and multiple preset standard word vectors to generate a target word segmentation model.
7. The method for decomposing urban operation indicators according to claim 6, characterized in that: The step of training the initial word segmentation model based on the plurality of preset standard indicator names and the plurality of preset standard word vectors to generate a target word segmentation model includes: Inputting a plurality of the preset standard indicator names into the initial word segmentation model, and determining a word vector to be verified output by the initial word segmentation model, wherein the word vector to be verified is a word vector generated by the initial word segmentation model based on the preset standard indicator name; Determining the word segmentation success rate of the initial word segmentation model based on each of the verification word vectors and the plurality of preset standard word vectors; When it is detected that the word segmentation success rate reaches a preset success rate threshold, the initial word segmentation model is determined as a target word segmentation model.
8. A terminal device, characterized in that: The device comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for decomposing urban operation indicators as described in any one of claims 1 to 7.
9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for decomposing urban operation indicators as described in any one of claims 1 to 7 are implemented.
10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method for decomposing urban operation indicators as claimed in any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Intelligent algorithm for standardized splitting and matching of evaluation standards based on civilized city evaluation projects
CN112733928A
Index data storage method, device and equipment, and storage medium
CN113722460A
Modeling method, server and storage medium
CN114490571A
Index name retrieval method and device, electronic equipment and storage medium
CN115617978A
