WO2020015171A1 - 电子装置、招商引资的目标对象确定方法、系统及存储介质 - Google Patents

电子装置、招商引资的目标对象确定方法、系统及存储介质 Download PDF

Info

Publication number
WO2020015171A1
WO2020015171A1 PCT/CN2018/107726 CN2018107726W WO2020015171A1 WO 2020015171 A1 WO2020015171 A1 WO 2020015171A1 CN 2018107726 W CN2018107726 W CN 2018107726W WO 2020015171 A1 WO2020015171 A1 WO 2020015171A1
Authority
WO
WIPO (PCT)
Prior art keywords
key information
item
target object
model
investment
Prior art date
Application number
PCT/CN2018/107726
Other languages
English (en)
French (fr)
Inventor
吴壮伟
Original Assignee
平安科技(深圳)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2020015171A1 publication Critical patent/WO2020015171A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/08Auctions

Definitions

  • the present application relates to the field of investment promotion, and in particular, to an electronic device, a method, a system, and a storage medium for determining a target object for investment promotion.
  • the present application proposes an electronic device, the electronic device includes a memory, and a processor connected to the memory, the processor is configured to execute a target object determination program for investment promotion stored on the memory.
  • the program for determining the target object of investment promotion is executed by the processor, the following steps are implemented:
  • A2 Obtain the second key information of each enterprise participating in the investment promotion project, and match the obtained second key information of each enterprise with the first key information to obtain the information of each enterprise and the investment promotion project. suitability;
  • A3 If the matching degree between an enterprise and the investment attraction project is greater than a predefined matching degree reference threshold, determine that the enterprise is the target object of investment invitation, and perform the target object level for the enterprise according to the predetermined target object classification method. classification;
  • A4. Determine whether the level of the enterprise meets the level of the investment promotion project according to the mapping relationship between the pre-stored target object level and the investment promotion target object. If so, the recommendation of the investment promotion project is automatically completed.
  • this application also proposes a method for determining a target object for investment promotion, which is characterized in that the method includes the following steps:
  • the present application also proposes a target object determination system for investment promotion, which is characterized in that the system includes:
  • An obtaining module configured to obtain first key information in text information of a predetermined investment promotion project
  • a matching module configured to obtain second key information of each enterprise participating in the investment promotion project, and match the obtained second key information of each enterprise with the first key information to obtain each enterprise and the investment invitation Matching degree of investment projects;
  • a classification module is used to determine that an enterprise is the target of investment promotion if the degree of matching between the enterprise and the investment attraction project is greater than a predefined reference threshold for matching investment, and to classify the enterprise according to a predetermined target object classification method. Classify target objects;
  • a determination module is used to determine whether the level of the enterprise meets the level of the investment promotion project according to the mapping relationship between the pre-stored target object level and the investment promotion target object. If so, the recommendation of the investment promotion project is automatically completed.
  • the present application also proposes a computer-readable storage medium storing a target object determination program for attracting investment, and the target object determination program for attracting investment may be processed by at least one Processor execution, so that the at least one processor performs the following steps:
  • the matching degree between an enterprise and the investment attraction project is greater than a predefined matching degree reference threshold, it is determined that the enterprise is the target object for investment promotion, and the target object level classification is performed for the enterprise according to the predetermined target object classification method.
  • mapping relationship between the pre-stored target object level and the investment promotion target object it is determined whether the level of the enterprise meets the level of the investment promotion project. If so, the recommendation of the investment promotion project is automatically completed.
  • the electronic device, the method, the system and the storage medium for determining the target of investment promotion proposed in the present application first obtain the first key information in the text information of the predetermined investment promotion project by obtaining the first key information;
  • the second key information of each enterprise is to match the obtained second key information of each enterprise with the first key information to obtain the matching degree between each enterprise and the investment attraction project;
  • the matching degree of the investment promotion project is greater than the predefined matching degree reference threshold, then the enterprise is determined as the target object of the investment promotion, and the target object level classification is performed on the enterprise according to the predetermined target object classification method; finally according to the pre-stored target
  • the mapping relationship between the object level and the investment promotion target object determines whether the level of the enterprise meets the level of the investment promotion project, and if it is satisfied, the recommendation of the investment promotion project is automatically completed. It can complete investment invitation through intelligent means, save a lot of labor costs, and improve the accuracy of the results.
  • FIG. 1 is a schematic diagram of an optional hardware architecture of an electronic device proposed by the present application.
  • FIG. 2 is a schematic diagram of a program module of a target object determination procedure for attracting investment in an embodiment of an electronic device of the present application
  • FIG. 3 is an implementation flowchart of a preferred embodiment of a method for determining a target object for investment promotion in this application.
  • first and second in this application are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. . Therefore, the features defined as “first” and “second” may explicitly or implicitly include at least one of the features.
  • technical solutions between the various embodiments can be combined with each other, but must be based on those that can be realized by a person of ordinary skill in the art. When the combination of technical solutions conflicts or cannot be realized, such a combination of technical solutions should be considered nonexistent. Is not within the scope of protection claimed in this application.
  • FIG. 1 is a schematic diagram of an optional hardware architecture of an electronic device according to the present application.
  • the electronic device 10 may include, but is not limited to, a memory 11, a processor 12, and a network interface 13 which may communicate with each other through a communication bus 14.
  • FIG. 1 only shows the electronic device 10 having components 11-14, but it should be understood that it is not required to implement all the illustrated components, and more or fewer components may be implemented instead.
  • the memory 11 includes at least one type of computer-readable storage medium.
  • the computer-readable storage medium includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, SD or DX memory, etc.), a random access memory (RAM), and a static memory.
  • the memory 11 may be an internal storage unit of the electronic device 10, such as a hard disk or a memory of the electronic device 10.
  • the memory 11 may also be an outsourced storage device of the electronic device 10, such as a plug-in hard disk, a smart media card (SMC), and a secure digital (SD) device. ) Cards, flash cards, etc.
  • the memory 11 may also include both the internal storage unit of the electronic device 10 and its outsourced storage device.
  • the memory 11 is generally used to store an operating system and various application software installed on the electronic device 10, such as a target object determination program for attracting investment.
  • the memory 11 can also be used to temporarily store various types of data that have been output or will be output.
  • the processor 12 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments.
  • the processor 12 is generally used to control the overall operation of the electronic device 10.
  • the processor 12 is configured to run program code or process data stored in the memory 11, such as a running target object determination program for attracting investment.
  • the network interface 13 may include a wireless network interface or a wired network interface.
  • the network interface 13 is generally used to establish a communication connection between the electronic device 10 and other electronic devices.
  • the communication bus 14 is used to implement a communication connection between the components 11-13.
  • FIG. 1 only shows the electronic device 10 having the components 11-14 and the target object determination program for attracting investment, but it should be understood that it is not required to implement all the illustrated components, and more or fewer components may be implemented instead. Components.
  • the electronic device 10 may further include a user interface (not shown in FIG. 1).
  • the user interface may include a display, an input unit such as a keyboard, and the user interface may further include a standard wired interface, a wireless interface, and the like.
  • the display may be an LED display, a liquid crystal display, a touch-type liquid crystal display, an OLED touch device, or the like. Further, the display may also be referred to as a display screen or a display unit, for displaying information processed in the electronic device 10 and for displaying a visualized user interface.
  • the electronic device 10 may further include an audio unit (the audio unit is not shown in FIG. 1), and the audio unit may be in the electronic device 10 in a call signal receiving mode, a call mode, a recording mode, and voice recognition. In the mode, the broadcast receiving mode, and the like, the received or stored audio data is converted into an audio signal. Further, the electronic device 10 may further include an audio output unit, and the audio output unit outputs the audio signal converted by the audio unit, and The audio output unit may also provide audio output (such as call signal reception sound, message reception sound, etc.) related to a specific function performed by the electronic device 10, and the audio output unit may include a speaker, a buzzer, and the like.
  • the audio output unit may include a speaker, a buzzer, and the like.
  • the electronic device 10 may further include an alarm unit (not shown in the figure), and the alarm unit may provide an output to notify the electronic device 10 of the occurrence of the event.
  • Typical events may include call reception, message reception, key signal input, touch input, and so on.
  • the alarm unit can provide output in different ways to notify the occurrence of an event.
  • the alarm unit may provide an output in the form of a vibration, and upon receiving a call, a message, or some other that may cause the electronic device 10 to enter the communication mode, the alarm unit may provide a tactile output (ie, vibration) to notify the user.
  • the text information of the predetermined investment promotion project includes the relevant topics of investment promotion and the content information corresponding to each topic.
  • the text information of the predetermined investment promotion project can be obtained through a given URL entry address and a page link. And download it; further, in this embodiment, the text information of the predetermined investment promotion project is analyzed according to the first key information labeling model that is pre-trained to obtain the first key information in the text information
  • the first key information includes the subject, industry classification, enterprise information keywords such as "listed company", “assets exceeding 100 million”, “professionals of not less than 50 people” and other enterprise information keywords, investment signal words such as Investment signal words and reward information such as “M & A” and “Plan to invest in the province”;
  • the pre-trained first key information labeling model is a neural network model
  • the training process of the first key information labeling model includes the following steps: E. Obtain a preset number of labeled Sample text information samples of investment promotion projects with key information and original text information corresponding to each text information sample;
  • the original text information corresponding to the text information sample of each item is divided into a training subset of the first proportion and a test subset of the second proportion;
  • the step of testing the first key information labeling model by using original text information of each item in the test subset includes:
  • the trained first key information labeling model is used to label the original text information of each item in the test subset, so as to obtain the third key information obtained through manual key information labeling of each item and the first key information.
  • Key information labeling model The probability value that the fourth key information obtained by automatically labeling the key information is equal;
  • the probability value that the third key information corresponding to the item is equal to the fourth key information is greater than the preset probability threshold, then a model accuracy test is performed on the item, and the item is manually labeled with the key information, To obtain the third key information corresponding to the item, and call the first key information labeling model to automatically mark the item to obtain the fourth key information corresponding to the item;
  • the calculated error value is less than a preset error threshold, determine that the result of the model accuracy test for the item is correct, or if the calculated error value is greater than or equal to the preset error threshold, determine the The result of the model accuracy test of the project is wrong;
  • the percentage of correct model accuracy test results for all model accuracy test results is greater than a preset percentage threshold, it is determined that the test of the first key information labeled model passes, or, if the correct model accuracy test results are correct If the percentage of the accuracy test results of all models is less than or equal to a preset percentage threshold, it is determined that the test of the first key information labeling model fails.
  • A2 Obtain the second key information of each enterprise participating in the investment promotion project, and match the obtained second key information of each enterprise with the first key information to obtain the information of each enterprise and the investment promotion project. suitability;
  • the key information labeling of the text information of each enterprise participating in the investment invitation project may be performed according to the second key information labeling model that is trained in advance to label the second key information corresponding to each enterprise.
  • the second key information labeling model is also a neural network model. The training process and testing process of the model are the same as the principle of the first key information labeling model, and are not repeated here.
  • A3 If the matching degree between an enterprise and the investment attraction project is greater than a predefined matching degree reference threshold, determine that the enterprise is the target object of investment invitation, and perform the target object level for the enterprise according to the predetermined target object classification method. classification;
  • the predetermined target object classification method is a density-based clustering algorithm.
  • the density-based clustering algorithm is a DBscan algorithm.
  • the specific density-based clustering algorithm includes: Data object information disclosed within a preset time (for example, within six months closest to the current point in time), such as business turnover, industry classification of winning bids, subject of bids, investment signal words and other data object information.
  • Target objects at preset levels for example, a listed company is a target object at the first level, a market value of over 100 million is a target object at the second level, and no fewer than 50 professionals are target objects at the third level. ;
  • Target objects of different preset levels are used as different input objects of the DBscan algorithm.
  • the target objects of different preset levels belong to different categories and can be divided into different discrete data according to the target objects of the preset level.
  • select an unvisited point to find out The number of times the point is visited (including the target object of the preset level) within the scanning radius e (including e).
  • the point (currently A target object of a preset level) forms a cluster (a cluster of clusters) with other points that have been visited within the scan radius e more than or equal to minp times, and the starting point is marked as the visited point. Then recursively, all unvisited points in the cluster are processed in the same way to expand the cluster.
  • the point is temporarily marked as a noise point (non-clustering point, corresponding to a preset level in this embodiment that is not related to the investment attraction project) (Target object), if the cluster is fully expanded, that is, all points in the cluster are marked as visited, then the same algorithm is used to process the unvisited points.
  • This cluster analysis method can be used to classify the target objects of investment promotion.
  • A4. Determine whether the level of the enterprise meets the level of the investment promotion project according to the mapping relationship between the pre-stored target object level and the investment promotion target object. If so, the recommendation of the investment promotion project is automatically completed.
  • the electronic device proposed in the present application first obtains the first key information in the text information of the predetermined investment promotion project by acquiring the first key information; and then obtains the second key information of each enterprise participating in the investment promotion project. , Matching the obtained second key information of each enterprise with the first key information to obtain a matching degree between each enterprise and the investment attraction project; again, if any enterprise has a matching degree with the investment attraction project greater than
  • the predefined matching reference threshold value determines that the enterprise is the target of investment promotion, and classifies the target of the enterprise according to the predetermined target object classification method; finally, according to the pre-stored target object level and the target of investment promotion
  • the mapping relationship between them determines whether the level of the enterprise meets the level of investment promotion projects. If so, the recommendation of investment promotion projects is automatically completed. It can complete investment invitation through intelligent means, save a lot of labor costs, and improve the accuracy of the results.
  • FIG. 2 is a schematic diagram of a program module of a program for determining a target object for investment promotion in an embodiment of an electronic device of the present application.
  • the target object determination program for investment promotion can be divided into an acquisition module 201, a matching module 202, a classification module 203, and a determination module 204 according to different functions implemented by its various parts.
  • the program module referred to in the present application refers to a series of computer program instruction segments capable of performing specific functions, which is more suitable than the program for describing the execution process of the target object determination program for attracting investment in the electronic device 10.
  • the functions or operation steps implemented by the modules 201-204 are similar to the above, which will not be described in detail here.
  • the obtaining module 201 is configured to obtain first key information in text information of a predetermined investment promotion project
  • the matching module 202 is configured to obtain second key information of each enterprise participating in the investment promotion project, and match the obtained second key information of each enterprise with the first key information to obtain each enterprise and the investment invitation. Matching degree of investment projects;
  • the classification module 203 is configured to determine that an enterprise is a target object for investment promotion if the matching degree between the enterprise and the investment attraction project is greater than a predefined matching degree reference threshold, and according to a predetermined target object classification method, determine the enterprise Classify target objects;
  • the determining module 204 is configured to determine whether the level of the enterprise meets the level of the investment promotion project according to the mapping relationship between the pre-stored target object level and the investment promotion target object, and if it is satisfied, the recommendation of the investment promotion project is automatically completed.
  • this application also proposes a method for determining the target object of investment promotion, as shown in FIG. 3.
  • the method for determining the target object of investment promotion includes the following steps:
  • the text information of the predetermined investment promotion project includes the relevant topics of investment promotion and the content information corresponding to each topic.
  • the text information of the predetermined investment promotion project can be obtained through a given URL entry address and a page link. And download it; further, in this embodiment, the text information of the predetermined investment promotion project is analyzed according to the first key information labeling model that is pre-trained to obtain the first key information in the text information
  • the first key information includes the subject, industry classification, enterprise information keywords such as "listed company", “assets exceeding 100 million”, “professionals of not less than 50 people” and other enterprise information keywords, investment signal words such as Investment signal words and reward information such as “M & A” and “Plan to invest in the province”;
  • the pre-trained first key information labeling model is a neural network model
  • the training process of the first key information labeling model includes the following steps: E. Obtain a preset number of labeled Sample text information samples of investment promotion projects with key information and original text information corresponding to each text information sample;
  • the original text information corresponding to the text information sample of each item is divided into a training subset of the first proportion and a test subset of the second proportion;
  • H Use the original text information of each item in the test subset to test the first key information labeling model. If the test passes, the training ends, or if the test fails, increase the training subset. Number of text message samples and perform steps E, F, G above.
  • the step of testing the first key information labeling model by using original text information of each item in the test subset includes:
  • the trained first key information labeling model is used to label the original text information of each item in the test subset, so as to obtain the third key information obtained through manual key information labeling of each item and the first key information.
  • Key information labeling model The probability value that the fourth key information obtained by automatically labeling the key information is equal;
  • the probability value that the third key information corresponding to the item is equal to the fourth key information is greater than the preset probability threshold, then a model accuracy test is performed on the item, and the item is manually labeled with the key information, To obtain the third key information corresponding to the item, and call the first key information labeling model to automatically mark the item to obtain the fourth key information corresponding to the item;
  • the calculated error value is less than a preset error threshold, determine that the result of the model accuracy test for the item is correct, or if the calculated error value is greater than or equal to the preset error threshold, determine the The result of the model accuracy test of the project is wrong;
  • the percentage of correct model accuracy test results for all model accuracy test results is greater than a preset percentage threshold, it is determined that the test of the first key information labeled model passes, or, if the correct model accuracy test results are correct If the percentage of the accuracy test results of all models is less than or equal to a preset percentage threshold, it is determined that the test of the first key information labeling model fails.
  • the key information labeling of the text information of each enterprise participating in the investment invitation project can be performed by using a second key information labeling model that is trained in advance to label the second key information corresponding to each enterprise.
  • the second key information labeling model is also a neural network model. The training process and testing process of the model are the same as the principle of the first key information labeling model, and are not repeated here.
  • the predetermined target object classification method is a density-based clustering algorithm.
  • the density-based clustering algorithm is a DBscan algorithm.
  • the specific density-based clustering algorithm includes: Data object information disclosed within a preset time (for example, within six months closest to the current point in time), such as business turnover, industry classification of winning bids, subject of bids, investment signal words and other data object information.
  • Target objects at preset levels for example, a listed company is a target object at the first level, a market value of over 100 million is a target object at the second level, and no fewer than 50 professionals are target objects at the third level. ;
  • Target objects of different preset levels are used as different input objects of the DBscan algorithm.
  • the target objects of different preset levels belong to different categories and can be divided into different discrete data according to the target objects of the preset level.
  • select an unvisited point to find out The number of times the point is visited (including the target object of the preset level) within the scanning radius e (including e).
  • the point (currently A target object of a preset level) forms a cluster (a cluster of clusters) with other points that have been visited within the scan radius e more than or equal to minp times, and the starting point is marked as the visited point. Then recursively, all unvisited points in the cluster are processed in the same way to expand the cluster.
  • the point is temporarily marked as a noise point (non-clustering point, corresponding to a preset level in this embodiment that is not related to the investment attraction project) (Target object), if the cluster is fully expanded, that is, all points in the cluster are marked as visited, then the same algorithm is used to process the unvisited points.
  • This cluster analysis method can be used to classify the target objects of investment promotion.
  • S304 Determine whether the level of the enterprise meets the level of the investment promotion project according to the mapping relationship between the pre-stored target object level and the investment promotion target object, and if so, the recommendation of the investment promotion project is automatically completed.
  • the method for determining the target object of the investment promotion proposed in the present application firstly obtains the first key information in the text information of the predetermined investment promotion project; and then obtains the enterprises participating in the investment promotion project.
  • the matching degree of the project is greater than the predefined matching degree reference threshold, then the enterprise is determined as the target object for investment promotion, and the target object level classification is performed for the enterprise according to the predetermined target object classification method; finally, according to the pre-stored target object level
  • the mapping relationship with the investment promotion target object determines whether the level of the enterprise meets the level of the investment promotion project. If so, the recommendation of the investment promotion project is automatically completed. It can complete investment invitation through intelligent means, save a lot of labor costs, and improve the accuracy of the results.
  • this application also proposes a computer-readable storage medium on which a target object determination program for investment promotion is stored.
  • the target object determination program for investment promotion is executed by a processor, the following operations are performed:
  • matching degree between an enterprise and the investment attraction project is greater than a predefined matching degree reference threshold, determining that the enterprise is the target object of the investment invitation, and classifying the enterprise according to the predetermined target object classification method;
  • mapping relationship between the pre-stored target object level and the investment promotion target object it is determined whether the level of the enterprise meets the level of the investment promotion project. If so, the recommendation of the investment promotion project is automatically completed.
  • the specific implementation of the computer-readable storage medium of the present application is basically the same as the above-mentioned electronic device and each embodiment of a method for determining a target object for attracting investment, and is not described in detail here.
  • the methods in the above embodiments can be implemented by means of software plus a necessary universal hardware platform, and of course, also by hardware, but in many cases the former is better.
  • Implementation Based on such an understanding, the technical solution of this application that is essentially or contributes to the existing technology can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, The optical disc) includes several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the embodiments of the present application.
  • a terminal device which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本申请公开了一种电子装置、招商引资的目标对象确定方法、系统以及存储介质,所述方法包括:获取获取预先确定的招商引资项目的文本信息中的第一关键信息;获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。能够通过智能化手段完成招商引资、节省大量的人力成本,且提高结果的准确性。

Description

电子装置、招商引资的目标对象确定方法、系统及存储介质
本申请要求于2018年7月19日提交中国专利局、申请号为201810798138.9,发明名称为“电子装置、至少引资的目标对象确定方法及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及招商投资领域,尤其涉及一种电子装置、招商引资的目标对象确定方法、系统及存储介质。
背景技术
随着计算机技术以及智能信息化的发展,很多领域利用机器智能化处理来替代繁琐的人工处理过程,不仅能够节省人力资源、降低成本,而且能个提高工作的准确率和稳定性。但是,目前在招商引资领域,依然主要是依赖于工作人员对相关政策的解读,并将解读之后的政策与企业的公开信息进行人工匹配以及筛选,缺乏高效的智能化手段,浪费大量的人力成本,且无法保证结果的准确性。
发明内容
有鉴于此,本申请提出一种电子装置、所述电子装置包括存储器、及与所述存储器连接的处理器,所述处理器用于执行所述存储器上存储的招商引资的目标对象确定程序,所述招商引资的目标对象确定程序被所述处理器执行时实现如下步骤:
A1、获取预先确定的招商引资项目的文本信息中的第一关键信息;
A2、获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;
A3、若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;
A4、根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。
此外,为实现上述目的,本申请还提出一种招商引资的目标对象确定方法,其特征在于,所述方法包括如下步骤:
S1、获取预先确定的招商引资项目的文本信息中的第一关键信息;
S2、获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;
S3、若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;
S4、根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。
此外,为实现上述目的,本申请还提出一种招商引资的目标对象确定系统,其特征在于,所述系统包括:
获取模块,用于获取预先确定的招商引资项目的文本信息中的第一关键信息;
匹配模块,用于获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;
分类模块,用于在若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;
确定模块,用于根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则 自动完成招商引资项目的推荐。
此外,为实现上述目的,本申请还提出一种计算机可读存储介质,所述计算机可读存储介质存储有招商引资的目标对象确定程序,所述招商引资的目标对象确定程序可被至少一个处理器执行,以使所述至少一个处理器执行如下步骤:
获取预先确定的招商引资项目的文本信息中的第一关键信息;
获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;
在若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;
根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。
本申请所提出的电子装置、招商引资的目标对象确定方法、系统及存储介质,首先通过获取获取预先确定的招商引资项目的文本信息中的第一关键信息;然后获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;再次若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;最后根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。能够通过智能化手段完成招商引资、节省大量的人力成本,且提高结果的准确性。
附图说明
图1是本申请提出的电子装置一可选的硬件架构的示意图;
图2是本申请电子装置一实施例中招商引资的目标对象确定程序的程序 模块示意图;
图3是本申请招商引资的目标对象确定方法较佳实施例的实施流程图。
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本申请进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本申请,并不用于限定本申请。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
需要说明的是,在本申请中涉及“第一”、“第二”等的描述仅用于描述目的,而不能理解为指示或暗示其相对重要性或者隐含指明所指示的技术特征的数量。由此,限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。另外,各个实施例之间的技术方案可以相互结合,但是必须是以本领域普通技术人员能够实现为基础,当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在,也不在本申请要求的保护范围之内。
参阅图1所示,是本申请提出的电子装置一可选的硬件架构示意图。本实施例中,电子装置10可包括,但不仅限于,可通过通信总线14相互通信连接存储器11、处理器12、网络接口13。需要指出的是,图1仅示出了具有组件11-14的电子装置10,但是应理解的是,并不要求实施所有示出的组件,可以替代的实施更多或者更少的组件。
其中,存储器11至少包括一种类型的计算机可读存储介质,计算机可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如,SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中,存储器11可以是电子装置10的内部存储单元,例如电子装置10的硬盘或内存。在另一些实施例中,存储器11也可以是电子装置10的外包存储设备,例如电子装置10 上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。当然,存储器11还可以既包括电子装置10的内部存储单元也包括其外包存储设备。本实施例中,存储器11通常用于存储安装于电子装置10的操作系统和各类应用软件,例如招商引资的目标对象确定程序等。此外,存储器11还可以用于暂时地存储已经输出或者将要输出的各类数据。
处理器12在一些实施例中可以是中央处理器(Central Processing Unit,CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。处理器12通常用于控制电子装置10的总体操作。本实施例中,处理器12用于运行存储器11中存储的程序代码或者处理数据,例如运行的招商引资的目标对象确定程序等。
网络接口13可包括无线网络接口或有线网络接口,网络接口13通常用于在电子装置10与其他电子设备之间建立通信连接。
通信总线14用于实现组件11-13之间的通信连接。
图1仅示出了具有组件11-14以及招商引资的目标对象确定程序的电子装置10,但是应理解的是,并不要求实施所有示出的组件,可以替代的实施更多或者更少的组件。
可选地,电子装置10还可以包括用户接口(图1中未示出),用户接口可以包括显示器、输入单元比如键盘,其中,用户接口还可以包括标准的有线接口、无线接口等。
可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED触摸器等。进一步地,显示器也可称为显示屏或显示单元,用于显示在电子装置10中处理信息以及用于显示可视化的用户界面。
可选地,在一些实施例中,电子装置10还可以包括音频单元(音频单元图1中未示出),音频单元可以在电子装置10处于呼叫信号接收模式、通话模式、记录模式、语音识别模式、广播接收模式等等模式下时,将接收的或者存储的音频数据转换为音频信号;进一步地,电子装置10还可以包括音频输出单元,音频输出单元将音频单元转换的音频信号输出,而且音频输出单元还可以提供与电子装置10执行的特定功能相关的音频输出(例如呼叫信号 接收声音、消息接收声音等等),音频输出单元可以包括扬声器、蜂鸣器等等。
可选地,在一些实施例中,电子装置10还可以包括警报单元(图中未示出),警报单元可以提供输出已将事件的发生通知给电子装置10。典型的事件可以包括呼叫接收、消息接收、键信号输入、触摸输入等等。除了音频或者视频输出之外,警报单元可以以不同的方式提供输出以通知事件的发生。例如,警报单元可以以震动的形式提供输出,当接收到呼叫、消息或一些其他可以使电子装置10进入通信模式时,警报单元可以提供触觉输出(即,振动)以将其通知给用户。
在一实施例中,存储器11中存储的招商引资的目标对象确定程序被处理器12执行时,实现如下操作:
A1、获取预先确定的招商引资项目的文本信息中的第一关键信息;
具体地,预先确定的招商引资项目的文本信息包括招商引资的相关主题以及各主题对应的内容信息,具体的,预先确定的招商引资项目的文本信息可以通过给定的网址入口地址,获取页面链接,进行下载得到;进一步地,在本实施例中,根据预先训练完成的第一关键信息标注模型,对预先确定的招商引资项目的文本信息进行分析,以获取该文本信息中的第一关键信息;具体地,所述第一关键信息包括主题、行业分类、企业信息关键字如“上市公司”“资产超过1亿”“专业人员不少于50人”等企业信息关键字、招商信号词语如“并购”、“计划在省内投资”等招商信号词语、奖励信息等;
具体地,在本实施例中,所述预先训练完成的第一关键信息标注模型为神经网络模型,所述第一关键信息标注模型的训练过程包括如下步骤:E、获取预设数量的已标注关键信息的招商引资项目的文本信息样本以及各个文本信息样本对应的原始文本信息;
F、将各个项目的文本信息样本对应的原始文本信息分为第一比例的训练子集和第二比例的测试子集;
G、利用所述训练子集中的各个项目的原始文本信息训练所述第一关键信息标注模型,以得到训练好的关键信息标注模型;
H、利用所述测试子集中的各个项目的原始文本信息对所述第一关键信息标注模型进行测试,若测试通过,则训练结束,或者,若测试不通过,则增加所述训练子集的文本信息样本的数量并重新执行上述步骤E、F、G及H。
具体地,在所述步骤H中,所述利用所述测试子集中的各个项目的原始文本信息对所述第一关键信息标注模型进行测试的步骤包括:
利用训练好的所述第一关键信息标注则模型对所述测试子集中的各个项目的原始文本信息进行标注,以得出各个项目通过人工进行关键信息标注得到的第三关键信息与通过第一关键信息标注模型自动进行关键信息标注得到的第四关键信息相等的概率值;
若有项目对应的所述第三关键信息与所述第四关键信息相等的概率值大于所述预设的概率阈值,则针对该项目进行模型准确性测试,将该项目进行人工标注关键信息,以得到该项目对应的第三关键信息,并调用第一关键信息标注模型自动标注该项目,以得到该项目对应的第四关键信息;
计算得到的该项目对应的第三关键信息与第四关键信息之间的误差值;
若所计算出的误差值小于预设的误差阈值,则确定针对该项目的模型准确性测试的结果为正确,或者,若所计算出的误差值大于或等于预设的误差阈值,则确定针对该项目的模型准确性测试的结果为错误;
若为正确的模型准确性测试结果占所有模型准确性测试结果的百分比大于预设百分比阈值,则确定对所述第一关键信息标注模型的测试通过,或者,若为正确的模型准确性测试结果占所有模型准确性测试结果的百分比小于或者等于预设百分比阈值,则确定对所述第一关键信息标注模型的测试不通过。
A2、获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;
具体地,可以根据预先训练完成的第二关键信息标注模型对参加所述招商引资项目的各企业的文本信息进行关键信息标注,以标注出各企业分别对应的第二关键信息。具体地,所述第二关键信息标注模型也为神经网络模型,所述模型的训练过程以及测试过程与所述第一关键信息标注模型的原理相同,在此,不再累述。
A3、若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;
具体地,预先确定的目标对象分类方法为基于密度的聚类算法,在一实施例中,基于密度的聚类算法为DBscan算法,具体的该基于密度的聚类算法包括:根据各目标对象在预设时间内(例如,离当前时间点最近的半年内)公开的数据对象信息,例如企业营业额、中标标的行业分类、投标标的的主题、招商信号词语等数据对象信息,将各目标对象分为预设级别的目标对象,例如上市公司为第一级别的目标对象、市值过亿为第二级别的目标对象、专业人员不少于50人为第三级别的目标对象等预设级别的目标对象;分别以不同预设级别的目标对象作为DBscan算法的不同输入对象,可以理解的是,不同预设级别的目标对象所属的类别不同,可以根据预设级别的目标对象分为不同的离散数据,并预设扫描半径e(例如,e=3,表示同一预设级别的目标对象包含的最少相同数据对象信息数)以及最小包含点数minp(例如,minp=5,表示5类不同预设级别的目标对象),然后任选一个未被访问的点(预设级别的目标对象)开始,找出在扫描半径e之内(包括e)该点被访问(访问该预设级别的目标对象)的次数,若在扫描半径e之内该点被访问的次数大于或等于minp,则该点(当前预设级别的目标对象)与其他在扫描半径e之内被访问的次数大于或等于minp次的点形成一个簇(一个聚类的簇),并且开始点被标记为已访问点。然后递归,以相同的方法处理该簇内所有未被访问的点,从而对簇进行扩展。若在扫描半径e之内该点被访问的次数小于minp,则该点暂时被标记作为噪声点(非聚类的点,对应在本实施例中为与招商引资项目不相关的预设级别的目标对象),若簇充分地被扩展,即簇内的所有点被标记为已访问,则用同样的算法去处理未被访问的点。通过这种聚类分析方法可以招商引资的目标对象进行级别分类。
A4、根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。
由上述事实施例可知,本申请提出的电子装置,首先通过获取获取预先确定的招商引资项目的文本信息中的第一关键信息;然后获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;再次若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值, 则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;最后根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。能够通过智能化手段完成招商引资、节省大量的人力成本,且提高结果的准确性。
此外,本申请的招商引资的目标对象确定程序依据其各部分所实现的功能不同,可用具有相同功能的程序模块进行描述。请参阅图2所示,是本申请电子装置一实施例中招商引资的目标对象确定程序的程序模块示意图。本实施例中,招商引资的目标对象确定程序依据其各部分所实现的功能的不同,可以被分割成获取模块201、匹配模块202、分类模块203以及确定模块204。由上面的描述可知,本申请所称的程序模块是指能够完成特定功能的一系列计算机程序指令段,比程序更适合于描述招商引资的目标对象确定程序在电子装置10中的执行过程。所述模块201-204所实现的功能或操作步骤均与上文类似,此处不再详述,示例性地,例如其中:
获取模块201用于获取预先确定的招商引资项目的文本信息中的第一关键信息;
匹配模块202用于获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;
分类模块203用于在若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;
确定模块204用于根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。
此外,本申请还提出一种招商引资的目标对象确定方法,请参阅图3所示,所述招商引资的目标对象确定方法包括如下步骤:
S301、获取预先确定的招商引资项目的文本信息中的第一关键信息;
具体地,预先确定的招商引资项目的文本信息包括招商引资的相关主题以及各主题对应的内容信息,具体的,预先确定的招商引资项目的文本信息 可以通过给定的网址入口地址,获取页面链接,进行下载得到;进一步地,在本实施例中,根据预先训练完成的第一关键信息标注模型,对预先确定的招商引资项目的文本信息进行分析,以获取该文本信息中的第一关键信息;具体地,所述第一关键信息包括主题、行业分类、企业信息关键字如“上市公司”“资产超过1亿”“专业人员不少于50人”等企业信息关键字、招商信号词语如“并购”、“计划在省内投资”等招商信号词语、奖励信息等;
具体地,在本实施例中,所述预先训练完成的第一关键信息标注模型为神经网络模型,所述第一关键信息标注模型的训练过程包括如下步骤:E、获取预设数量的已标注关键信息的招商引资项目的文本信息样本以及各个文本信息样本对应的原始文本信息;
F、将各个项目的文本信息样本对应的原始文本信息分为第一比例的训练子集和第二比例的测试子集;
G、利用所述训练子集中的各个项目的原始文本信息训练所述第一关键信息标注模型,以得到训练好的关键信息标注模型;
H、利用所述测试子集中的各个项目的原始文本信息对所述第一关键信息标注模型进行测试,若测试通过,则训练结束,或者,若测试不通过,则增加所述训练子集的文本信息样本的数量并重新执行上述步骤E、F、G。
具体地,在所述步骤H中,所述利用所述测试子集中的各个项目的原始文本信息对所述第一关键信息标注模型进行测试的步骤包括:
利用训练好的所述第一关键信息标注则模型对所述测试子集中的各个项目的原始文本信息进行标注,以得出各个项目通过人工进行关键信息标注得到的第三关键信息与通过第一关键信息标注模型自动进行关键信息标注得到的第四关键信息相等的概率值;
若有项目对应的所述第三关键信息与所述第四关键信息相等的概率值大于所述预设的概率阈值,则针对该项目进行模型准确性测试,将该项目进行人工标注关键信息,以得到该项目对应的第三关键信息,并调用第一关键信息标注模型自动标注该项目,以得到该项目对应的第四关键信息;
计算得到的该项目对应的第三关键信息与第四关键信息之间的误差值;
若所计算出的误差值小于预设的误差阈值,则确定针对该项目的模型准确性测试的结果为正确,或者,若所计算出的误差值大于或等于预设的误差阈值,则确定针对该项目的模型准确性测试的结果为错误;
若为正确的模型准确性测试结果占所有模型准确性测试结果的百分比大于预设百分比阈值,则确定对所述第一关键信息标注模型的测试通过,或者,若为正确的模型准确性测试结果占所有模型准确性测试结果的百分比小于或者等于预设百分比阈值,则确定对所述第一关键信息标注模型的测试不通过。
S302、获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;
具体地,可以通过预先训练完成的第二关键信息标注模型对参加所述招商引资项目的各企业的文本信息进行关键信息标注,以标注出各企业分别对应的第二关键信息。具体地,所述第二关键信息标注模型也为神经网络模型,所述模型的训练过程以及测试过程与所述第一关键信息标注模型的原理相同,在此,不再累述。
S303、若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;
具体地,预先确定的目标对象分类方法为基于密度的聚类算法,在一实施例中,基于密度的聚类算法为DBscan算法,具体的该基于密度的聚类算法包括:根据各目标对象在预设时间内(例如,离当前时间点最近的半年内)公开的数据对象信息,例如企业营业额、中标标的行业分类、投标标的的主题、招商信号词语等数据对象信息,将各目标对象分为预设级别的目标对象,例如上市公司为第一级别的目标对象、市值过亿为第二级别的目标对象、专业人员不少于50人为第三级别的目标对象等预设级别的目标对象;分别以不同预设级别的目标对象作为DBscan算法的不同输入对象,可以理解的是,不同预设级别的目标对象所属的类别不同,可以根据预设级别的目标对象分为不同的离散数据,并预设扫描半径e(例如,e=3,表示同一预设级别的目标对象包含的最少相同数据对象信息数)以及最小包含点数minp(例如,minp=5,表示5类不同预设级别的目标对象),然后任选一个未被访问的点(预设级别 的目标对象)开始,找出在扫描半径e之内(包括e)该点被访问(访问该预设级别的目标对象)的次数,若在扫描半径e之内该点被访问的次数大于或等于minp,则该点(当前预设级别的目标对象)与其他在扫描半径e之内被访问的次数大于或等于minp次的点形成一个簇(一个聚类的簇),并且开始点被标记为已访问点。然后递归,以相同的方法处理该簇内所有未被访问的点,从而对簇进行扩展。若在扫描半径e之内该点被访问的次数小于minp,则该点暂时被标记作为噪声点(非聚类的点,对应在本实施例中为与招商引资项目不相关的预设级别的目标对象),若簇充分地被扩展,即簇内的所有点被标记为已访问,则用同样的算法去处理未被访问的点。通过这种聚类分析方法可以招商引资的目标对象进行级别分类。
S304、根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。
由上述事实施例可知,本申请提出的招商引资的目标对象确定方法,首先通过获取获取预先确定的招商引资项目的文本信息中的第一关键信息;然后获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;再次若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;最后根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。能够通过智能化手段完成招商引资、节省大量的人力成本,且提高结果的准确性。
此外,本申请还提出一种计算机可读存储介质,所述计算机可读存储介质上存储有招商引资的目标对象确定程序,所述招商引资的目标对象确定程序被处理器执行时实现如下操作:
获取预先确定的招商引资项目的文本信息中的第一关键信息;
获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;
若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;
根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。
本申请计算机可读存储介质具体实施方式与上述电子装置以及招商引资的目标对象确定方法各实施例基本相同,在此不作累述。
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种电子装置,其特征在于,所述电子装置包括存储器、及与所述存储器连接的处理器,所述处理器用于执行所述存储器上存储的招商引资的目标对象确定程序,所述招商引资的目标对象确定程序被所述处理器执行时实现如下步骤:
    A1、获取预先确定的招商引资项目的文本信息中的第一关键信息;
    A2、获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;
    A3、若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;
    A4、根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。
  2. 如权利要求1所述的电子装置,其特征在于,所述步骤A1包括:
    根据预先训练完成的第一关键信息标注模型,对预先确定的招商引资项目的文本信息进行分析,以获取该文本信息中的第一关键信息。
  3. 如权利要求2所述的电子装置,其特征在于,所述预先训练完成的第一关键信息标注模型为神经网络模型,所述第一关键信息标注模型的训练过程包括如下步骤:
    E1、获取预设数量的已标注关键信息的招商引资项目的文本信息样本以及各个文本信息样本对应的原始文本信息;
    F1、将各个项目的文本信息样本对应的原始文本信息分为第一比例的训练子集和第二比例的测试子集;
    G1、利用所述训练子集中的各个项目的原始文本信息训练所述第一关键信息标注模型,以得到训练好的关键信息标注模型;
    H1、利用所述测试子集中的各个项目的原始文本信息对所述第一关键信息标注模型进行测试,若测试通过,则训练结束,或者,若测试不通过,则 增加所述训练子集的文本信息样本的数量并重新执行上述步骤E1、F1、G1及H1。
  4. 如权利要求3所述的电子装置,其特征在于,在所述步骤H1中,所述利用所述测试子集中的各个项目的原始文本信息对所述第一关键信息标注模型进行测试的步骤包括:
    利用训练好的所述第一关键信息标注则模型对所述测试子集中的各个项目的原始文本信息进行标注,以得出各个项目通过人工进行关键信息标注得到的第三关键信息与通过第一关键信息标注模型自动进行关键信息标注得到的第四关键信息相等的概率值;
    若有项目对应的所述第三关键信息与所述第四关键信息相等的概率值大于所述预设的概率阈值,则针对该项目进行模型准确性测试,将该项目进行人工标注关键信息,以得到该项目对应的第三关键信息,并调用第一关键信息标注模型自动标注该项目,以得到该项目对应的第四关键信息;
    计算得到的该项目对应的第三关键信息与第四关键信息之间的误差值;
    若所计算出的误差值小于预设的误差阈值,则确定针对该项目的模型准确性测试的结果为正确,或者,若所计算出的误差值大于或等于预设的误差阈值,则确定针对该项目的模型准确性测试的结果为错误;
    若为正确的模型准确性测试结果占所有模型准确性测试结果的百分比大于预设百分比阈值,则确定对所述第一关键信息标注模型的测试通过,或者,若为正确的模型准确性测试结果占所有模型准确性测试结果的百分比小于或者等于预设百分比阈值,则确定对所述第一关键信息标注模型的测试不通过。
  5. 如权利要求1所述的电子装置,其特征在于,在所述步骤A3中,所述预先确定的目标对象分类方法为基于密度的聚类算法,所述基于密度的聚类算法为DBscan算法。
  6. 一种招商引资的目标对象确定方法,其特征在于,所述方法包括如下步骤:
    S1、获取预先确定的招商引资项目的文本信息中的第一关键信息;
    S2、获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;
    S3、若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;
    S4、根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。
  7. 如权利要求6所述的招商引资的目标对象确定方法,其特征在于,所述步骤S1包括:
    根据预先训练完成的第一关键信息标注模型,对预先确定的招商引资项目的文本信息进行分析,以获取该文本信息中的第一关键信息。
  8. 如权利要求7所述的招商引资的目标对象确定方法,其特征在于,所述预先训练完成的第一关键信息标注模型为神经网络模型,所述第一关键信息标注模型的训练过程包括如下步骤:
    E2、获取预设数量的已标注关键信息的招商引资项目的文本信息样本以及各个文本信息样本对应的原始文本信息;
    F2、将各个项目的文本信息样本对应的原始文本信息分为第一比例的训练子集和第二比例的测试子集;
    G2、利用所述训练子集中的各个项目的原始文本信息训练所述第一关键信息标注模型,以得到训练好的关键信息标注模型;
    H2、利用所述测试子集中的各个项目的原始文本信息对所述第一关键信息标注模型进行测试,若测试通过,则训练结束,或者,若测试不通过,则增加所述训练子集的文本信息样本的数量并重新执行上述步骤E2、F2、G2及H2。
  9. 如权利要求8所述的招商引资的目标对象确定方法,其特征在于,在所述步骤H2中,所述利用所述测试子集中的各个项目的原始文本信息对所述第一关键信息标注模型进行测试的步骤包括:
    利用训练好的所述第一关键信息标注则模型对所述测试子集中的各个项目的原始文本信息进行标注,以得出各个项目通过人工进行关键信息标注得到的第三关键信息与通过第一关键信息标注模型自动进行关键信息标注得到的第四关键信息相等的概率值;
    若有项目对应的所述第三关键信息与所述第四关键信息相等的概率值大于所述预设的概率阈值,则针对该项目进行模型准确性测试,将该项目进行人工标注关键信息,以得到该项目对应的第三关键信息,并调用第一关键信息标注模型自动标注该项目,以得到该项目对应的第四关键信息;
    计算得到的该项目对应的第三关键信息与第四关键信息之间的误差值;
    若所计算出的误差值小于预设的误差阈值,则确定针对该项目的模型准确性测试的结果为正确,或者,若所计算出的误差值大于或等于预设的误差阈值,则确定针对该项目的模型准确性测试的结果为错误;
    若为正确的模型准确性测试结果占所有模型准确性测试结果的百分比大于预设百分比阈值,则确定对所述第一关键信息标注模型的测试通过,或者,若为正确的模型准确性测试结果占所有模型准确性测试结果的百分比小于或者等于预设百分比阈值,则确定对所述第一关键信息标注模型的测试不通过。
  10. 如权利要求6所述的招商引资的目标对象确定方法,其特征在于,在所述步骤S3中,所述预先确定的目标对象分类方法为基于密度的聚类算法,所述基于密度的聚类算法为DBscan算法。
  11. 一种招商引资的目标对象确定系统,其特征在于,所述系统包括:
    获取模块,用于获取预先确定的招商引资项目的文本信息中的第一关键信息;
    匹配模块,用于获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;
    分类模块,用于在若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;
    确定模块,用于根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。
  12. 如权利要求11所述的招商引资的目标对象确定系统,其特征在于,所述获取模块根据预先训练完成的第一关键信息标注模型,对预先确定的招商引资项目的文本信息进行分析,以获取该文本信息中的第一关键信息。
  13. 如权利要求12所述的招商引资的目标对象确定系统,其特征在于,所述预先训练完成的第一关键信息标注模型为神经网络模型,所述第一关键信息标注模型的训练过程包括如下步骤:
    E3、获取预设数量的已标注关键信息的招商引资项目的文本信息样本以及各个文本信息样本对应的原始文本信息;
    F3、将各个项目的文本信息样本对应的原始文本信息分为第一比例的训练子集和第二比例的测试子集;
    G3、利用所述训练子集中的各个项目的原始文本信息训练所述第一关键信息标注模型,以得到训练好的关键信息标注模型;
    H3、利用所述测试子集中的各个项目的原始文本信息对所述第一关键信息标注模型进行测试,若测试通过,则训练结束,或者,若测试不通过,则增加所述训练子集的文本信息样本的数量并重新执行上述步骤E3、F3、G3及H3。
  14. 如权利要求13所述的招商引资的目标对象确定系统,其特征在于,在所述步骤H3中,所述利用所述测试子集中的各个项目的原始文本信息对所述第一关键信息标注模型进行测试的步骤包括:
    利用训练好的所述第一关键信息标注则模型对所述测试子集中的各个项目的原始文本信息进行标注,以得出各个项目通过人工进行关键信息标注得到的第三关键信息与通过第一关键信息标注模型自动进行关键信息标注得到的第四关键信息相等的概率值;
    若有项目对应的所述第三关键信息与所述第四关键信息相等的概率值大于所述预设的概率阈值,则针对该项目进行模型准确性测试,将该项目进行人工标注关键信息,以得到该项目对应的第三关键信息,并调用第一关键信息标注模型自动标注该项目,以得到该项目对应的第四关键信息;
    计算得到的该项目对应的第三关键信息与第四关键信息之间的误差值;
    若所计算出的误差值小于预设的误差阈值,则确定针对该项目的模型准确性测试的结果为正确,或者,若所计算出的误差值大于或等于预设的误差阈值,则确定针对该项目的模型准确性测试的结果为错误;
    若为正确的模型准确性测试结果占所有模型准确性测试结果的百分比大于预设百分比阈值,则确定对所述第一关键信息标注模型的测试通过,或者, 若为正确的模型准确性测试结果占所有模型准确性测试结果的百分比小于或者等于预设百分比阈值,则确定对所述第一关键信息标注模型的测试不通过。
  15. 如权利要求11所述的招商引资的目标对象确定系统,其特征在于,所述预先确定的目标对象分类方法为基于密度的聚类算法,所述基于密度的聚类算法为DBscan算法。
  16. 一种计算机可读存储介质,所述计算机可读存储介质存储有招商引资的目标对象确定程序,所述招商引资的目标对象确定程序可被至少一个处理器执行,以使所述至少一个处理器执行如下步骤:
    获取预先确定的招商引资项目的文本信息中的第一关键信息;
    获取参加所述招商引资项目的各企业的第二关键信息,分别将获取的各企业的第二关键信息与所述第一关键信息进行匹配,以得到各个企业与所述招商引资项目的匹配度;
    若有企业与所述招商引资项目的匹配度大于预定义的匹配度参考阈值,则确定该企业为招商引资的目标对象,根据预先确定的目标对象分类方法,对该企业进行目标对象级别分类;
    根据预先存储的目标对象级别与招商引资目标对象之间的映射关系,确定该企业的级别是否满足招商引资项目的级别,若满足,则自动完成招商引资项目的推荐。
  17. 如权利要求16所述的计算机可读存储介质,其特征在于,所述获取预先确定的招商引资项目的文本信息中的第一关键信息的步骤,包括:
    根据预先训练完成的第一关键信息标注模型,对预先确定的招商引资项目的文本信息进行分析,以获取该文本信息中的第一关键信息。
  18. 如权利要求17所述的计算机可读存储介质,其特征在于,所述预先训练完成的第一关键信息标注模型为神经网络模型,所述第一关键信息标注模型的训练过程包括如下步骤:
    E4、获取预设数量的已标注关键信息的招商引资项目的文本信息样本以及各个文本信息样本对应的原始文本信息;
    F4、将各个项目的文本信息样本对应的原始文本信息分为第一比例的训练子集和第二比例的测试子集;
    G4、利用所述训练子集中的各个项目的原始文本信息训练所述第一关键信息标注模型,以得到训练好的关键信息标注模型;
    H4、利用所述测试子集中的各个项目的原始文本信息对所述第一关键信息标注模型进行测试,若测试通过,则训练结束,或者,若测试不通过,则增加所述训练子集的文本信息样本的数量并重新执行上述步骤E4、F4、G4及H4。
  19. 如权利要求18所述的计算机可读存储介质,其特征在于,在所述步骤H4中,所述利用所述测试子集中的各个项目的原始文本信息对所述第一关键信息标注模型进行测试的步骤包括:
    利用训练好的所述第一关键信息标注则模型对所述测试子集中的各个项目的原始文本信息进行标注,以得出各个项目通过人工进行关键信息标注得到的第三关键信息与通过第一关键信息标注模型自动进行关键信息标注得到的第四关键信息相等的概率值;
    若有项目对应的所述第三关键信息与所述第四关键信息相等的概率值大于所述预设的概率阈值,则针对该项目进行模型准确性测试,将该项目进行人工标注关键信息,以得到该项目对应的第三关键信息,并调用第一关键信息标注模型自动标注该项目,以得到该项目对应的第四关键信息;
    计算得到的该项目对应的第三关键信息与第四关键信息之间的误差值;
    若所计算出的误差值小于预设的误差阈值,则确定针对该项目的模型准确性测试的结果为正确,或者,若所计算出的误差值大于或等于预设的误差阈值,则确定针对该项目的模型准确性测试的结果为错误;
    若为正确的模型准确性测试结果占所有模型准确性测试结果的百分比大于预设百分比阈值,则确定对所述第一关键信息标注模型的测试通过,或者,若为正确的模型准确性测试结果占所有模型准确性测试结果的百分比小于或者等于预设百分比阈值,则确定对所述第一关键信息标注模型的测试不通过。
  20. 如权利要求16所述的计算机可读存储介质,其特征在于,所述预先确定的目标对象分类方法为基于密度的聚类算法,所述基于密度的聚类算法为DBscan算法。
PCT/CN2018/107726 2018-07-19 2018-09-26 电子装置、招商引资的目标对象确定方法、系统及存储介质 WO2020015171A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810798138.9 2018-07-19
CN201810798138.9A CN110020191A (zh) 2018-07-19 2018-07-19 电子装置、招商引资的目标对象确定方法及存储介质

Publications (1)

Publication Number Publication Date
WO2020015171A1 true WO2020015171A1 (zh) 2020-01-23

Family

ID=67188361

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/107726 WO2020015171A1 (zh) 2018-07-19 2018-09-26 电子装置、招商引资的目标对象确定方法、系统及存储介质

Country Status (2)

Country Link
CN (1) CN110020191A (zh)
WO (1) WO2020015171A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112528007B (zh) * 2019-09-19 2023-04-07 中冶赛迪信息技术(重庆)有限公司 一种招商项目的目标企业的确认方法及确认装置
CN110728540A (zh) * 2019-10-10 2020-01-24 华夏幸福产业投资有限公司 一种企业推荐方法、装置、设备和介质
CN112396550A (zh) * 2020-11-26 2021-02-23 深圳市中博科创信息技术有限公司 一种智慧招商平台的构建管理方法
CN116127346A (zh) * 2021-01-20 2023-05-16 国义招标股份有限公司 一种不依赖历史信息的密度聚类处理方法、设备及介质
CN117573877B (zh) * 2024-01-17 2024-03-22 安徽省优质采科技发展有限责任公司 一种供应链协同管理平台物资数据处理方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1889078A (zh) * 2006-06-22 2007-01-03 蔡征兵 一种网络搜索平台发布信息并按实际位置排序的方法
CN101127050A (zh) * 2007-07-03 2008-02-20 北京大学 一种从网页中自动提取网站拥有者行政属地信息的方法
CN106412026A (zh) * 2016-09-09 2017-02-15 上海润吧信息技术有限公司 一种基于企业服务外包的公共网络服务系统
CN106960063A (zh) * 2017-04-20 2017-07-18 广州优亚信息技术有限公司 一种针对招商引资领域的互联网情报抓取和推荐系统
CN107948596A (zh) * 2017-11-27 2018-04-20 江西文文网络科技有限公司 一种乡镇管理系统

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8650170B2 (en) * 2011-06-22 2014-02-11 Verisign, Inc. Systems and methods for inter-object pattern matching
CN104375998A (zh) * 2013-08-13 2015-02-25 王建平 一种智能化的项目匹配分析工具及其实现方法
CN105718580A (zh) * 2016-01-25 2016-06-29 江苏国泰新点软件有限公司 一种提供招投标信息搜索服务的方法和装置
CN106919702B (zh) * 2017-02-14 2020-02-11 北京时间股份有限公司 基于文档的关键词推送方法及装置
CN107945024B (zh) * 2017-12-12 2020-08-21 厦门市美亚柏科信息股份有限公司 识别互联网金融借贷企业经营异常的方法、终端设备及存储介质
CN108197811A (zh) * 2018-01-04 2018-06-22 四川隧唐科技股份有限公司 工程跟踪方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1889078A (zh) * 2006-06-22 2007-01-03 蔡征兵 一种网络搜索平台发布信息并按实际位置排序的方法
CN101127050A (zh) * 2007-07-03 2008-02-20 北京大学 一种从网页中自动提取网站拥有者行政属地信息的方法
CN106412026A (zh) * 2016-09-09 2017-02-15 上海润吧信息技术有限公司 一种基于企业服务外包的公共网络服务系统
CN106960063A (zh) * 2017-04-20 2017-07-18 广州优亚信息技术有限公司 一种针对招商引资领域的互联网情报抓取和推荐系统
CN107948596A (zh) * 2017-11-27 2018-04-20 江西文文网络科技有限公司 一种乡镇管理系统

Also Published As

Publication number Publication date
CN110020191A (zh) 2019-07-16

Similar Documents

Publication Publication Date Title
WO2020015171A1 (zh) 电子装置、招商引资的目标对象确定方法、系统及存储介质
CN107251060B (zh) 针对序列标签器的预训练和/或迁移学习
US8170466B2 (en) System and method for automated assessment of constrained constructed responses
CN107423278B (zh) 评价要素的识别方法、装置及系统
US10147020B1 (en) System and method for computational disambiguation and prediction of dynamic hierarchical data structures
JP2019125145A (ja) 情報処理装置、情報処理方法、及び情報処理プログラム
CN109616101B (zh) 声学模型训练方法、装置、计算机设备和可读存储介质
CN113157899B (zh) 一种大数据画像分析方法、服务器及可读存储介质
WO2020143301A1 (zh) 一种训练样本有效性检测方法、计算机设备及计算机非易失性存储介质
WO2021151305A1 (zh) 基于缺失数据的样本分析方法、装置、电子设备及介质
CN111144079A (zh) 一种智能获取学习资源的方法、装置、打印机和存储介质
CN107844531B (zh) 答案输出方法、装置和计算机设备
US11769013B2 (en) Machine learning based tenant-specific chatbots for performing actions in a multi-tenant system
CN112101231A (zh) 学习行为的监控方法、终端、小程序以及服务器
CN111325031A (zh) 简历解析方法及装置
WO2022126965A1 (zh) 智能问答方法、装置、设备及存储介质
CN113157871B (zh) 应用人工智能的新闻舆情文本处理方法、服务器及介质
WO2021174814A1 (zh) 众包任务的答案验证方法、装置、计算机设备及存储介质
CN112214770B (zh) 恶意样本的识别方法、装置、计算设备以及介质
CN111784053A (zh) 交易风险检测方法、设备及可读存储介质
CN110263135B (zh) 一种数据交换匹配方法、装置、介质和电子设备
CN114492310B (zh) 文本标注方法、文本标注装置、电子设备和存储介质
CN111967235B (zh) 表单处理方法、装置、计算机设备及存储介质
CN114782110A (zh) 基于逻辑回归二分类与jmts的需求挖掘方法及系统
US20200073891A1 (en) Systems and methods for classifying data in high volume data streams

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18926510

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 18.05.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18926510

Country of ref document: EP

Kind code of ref document: A1