CN109785064A - A kind of mobile e-business recommended method and system based on Multi-source Information Fusion - Google Patents
A kind of mobile e-business recommended method and system based on Multi-source Information Fusion Download PDFInfo
- Publication number
- CN109785064A CN109785064A CN201910030517.8A CN201910030517A CN109785064A CN 109785064 A CN109785064 A CN 109785064A CN 201910030517 A CN201910030517 A CN 201910030517A CN 109785064 A CN109785064 A CN 109785064A
- Authority
- CN
- China
- Prior art keywords
- evidence
- data
- original
- mobile
- information
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000004927 fusion Effects 0.000 title claims abstract description 37
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000001228 spectrum Methods 0.000 claims description 9
- 230000015572 biosynthetic process Effects 0.000 claims description 8
- 238000003786 synthesis reaction Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000005311 autocorrelation function Methods 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 5
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000007418 data mining Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本发明公开了一种基于多源信息融合的移动电子商务推荐方法，包括：S1：从多个信息源获取用户信息和对应的消费数据，对获取的用户信息和对应的消费数据进行预处理，以获取原始证据体，所述原始证据体被划分成若干类；S2：基于所述原始证据体，通过径向基函数和神经网络算法，计算原始证据体中每类数据的证据权重，所述证据权重用于区分每类数据的推荐价值；S3：根据所述证据权重，运用D‑S证据理论对原始证据体进行信息融合，以获得新的证据体；S4：采用功率谱估计方法对所述新的证据体进行处理，以获取推荐决策。本发明能够有效增加推荐准确性、间接性和覆盖率，提高推荐服务性能。
The invention discloses a mobile e-commerce recommendation method based on multi-source information fusion, comprising: S1: acquiring user information and corresponding consumption data from multiple information sources, and preprocessing the acquired user information and corresponding consumption data, In order to obtain the original body of evidence, the original body of evidence is divided into several categories; S2: Based on the original body of evidence, through radial basis function and neural network algorithm, calculate the evidence weight of each type of data in the original body of evidence, the The weight of evidence is used to distinguish the recommended value of each type of data; S3: According to the weight of evidence, use D-S evidence theory to fuse the original body of evidence to obtain a new body of evidence; The new body of evidence mentioned is processed to obtain a recommendation decision. The invention can effectively increase the recommendation accuracy, indirectness and coverage, and improve the performance of the recommendation service.
Description
技术领域technical field
本发明涉及信息融合技术领域，具体而言涉及一种基于多源信息融合的移动电子商务推荐方法和系统。The invention relates to the technical field of information fusion, in particular to a mobile e-commerce recommendation method and system based on multi-source information fusion.
背景技术Background technique
随着用户消费习惯的变化，移动电子商务已成为一种趋势。然而，连续生成大量数据不仅对于消费者在搜索有意义的产品时不方便，而且还意味着很少购买一些产品。缺乏对用户和资源信息的深入挖掘已成为制约移动商务推荐系统预测分析的主要瓶颈。With the change of users' consumption habits, mobile e-commerce has become a trend. However, the continuous generation of large amounts of data is not only inconvenient for consumers to search for meaningful products, but also means that some products are rarely purchased. The lack of in-depth mining of user and resource information has become the main bottleneck restricting the predictive analysis of mobile commerce recommendation systems.
为了解决上述问题发明了推荐系统，并被电子商务从业者广泛应用，现已成为信息科学和决策支持系统的重要研究课题。目前，推荐系统的研究一般包括基于内容的过滤(CBF)，协同过滤(CF)和其他数据挖掘技术，如决策树，关联规则和语义方法。In order to solve the above problems, the recommendation system was invented and widely used by e-commerce practitioners. It has now become an important research topic in information science and decision support systems. Currently, research on recommender systems generally includes content-based filtering (CBF), collaborative filtering (CF) and other data mining techniques, such as decision trees, association rules, and semantic methods.
现有的电子商务推荐系统存在着两大问题。首先，电子商务推荐系统不够深入，无法在多源挖掘中挖掘消费者的在线行为。推荐系统只关注产品和消费者在购物平台上的购物行为的信息，因此，推荐的准确性是有限的。其次，现有的移动电子商务推荐系统没有整合用户位置信息，推荐的覆盖性是有限的。There are two major problems in the existing e-commerce recommendation systems. First, e-commerce recommendation systems are not deep enough to mine consumers' online behaviors in multi-source mining. Recommender systems only focus on information about products and consumers' shopping behaviors on shopping platforms, so the accuracy of recommendations is limited. Secondly, the existing mobile e-commerce recommendation systems do not integrate user location information, and the coverage of recommendations is limited.
Yager、Gregor和许多其他学者深入研究了多源信息融合框架，信息分类，自动推理，异构数据处理，云计算和点对点(P2P)信息融合的网络信任模型。大多数信息融合模型都是基于美国国防部建立的JDL模型，它实现了从四个不同处理层面融合多源信息的要求。随着多源信息融合技术研究的发展，它已被用于模式识别，数据挖掘，知识发现等方面。然而，基于移动电子商务推荐系统中的位置的多源信息融合的研究较少。Yager, Gregor, and many other scholars have deeply studied multi-source information fusion frameworks, information classification, automated reasoning, heterogeneous data processing, cloud computing, and network trust models for peer-to-peer (P2P) information fusion. Most of the information fusion models are based on the JDL model established by the U.S. Department of Defense, which fulfills the requirements of fusing multi-source information from four different processing levels. With the development of multi-source information fusion technology research, it has been used in pattern recognition, data mining, knowledge discovery and so on. However, there are few studies on location-based multi-source information fusion in mobile e-commerce recommender systems.
发明内容SUMMARY OF THE INVENTION
本发明目的在于提供一种基于多源信息融合的移动电子商务推荐方法和系统，首先根据消费平台内外的两种类型信息，获取用户信息和数据；其次通过径向基函数和神经网络算法，计算推荐证据权重；再运用D-S证据理论，采用可行度来修改证据体，进行信息融合；最后综合考虑信息的时效性，稳定性，全面性等众多因素，采用功率谱估计方法处理融合结果，最终得到推荐决策。本发明能够有效增加推荐准确性、间接性和覆盖率，提高推荐服务性能。The purpose of the present invention is to provide a mobile e-commerce recommendation method and system based on multi-source information fusion. First, user information and data are obtained according to two types of information inside and outside the consumption platform; secondly, the radial basis function and neural network algorithm are used to calculate The weight of evidence is recommended; then the D-S evidence theory is used to modify the evidence body and perform information fusion; finally, considering the timeliness, stability, comprehensiveness and other factors of the information, the power spectrum estimation method is used to process the fusion results, and finally get Recommendation decision. The invention can effectively increase the recommendation accuracy, indirectness and coverage, and improve the performance of the recommendation service.
为达成上述目的，结合图1，本发明提出一种基于多源信息融合的移动电子商务推荐方法，所述方法包括：In order to achieve the above object, with reference to FIG. 1, the present invention proposes a mobile e-commerce recommendation method based on multi-source information fusion, the method includes:
S1：从多个信息源获取用户信息和对应的消费数据，对获取的用户信息和对应的消费数据进行预处理，以获取原始证据体，所述原始证据体被划分成若干类；S1: Obtain user information and corresponding consumption data from multiple information sources, and preprocess the obtained user information and corresponding consumption data to obtain an original body of evidence, which is divided into several categories;
S2：基于所述原始证据体，通过径向基函数和神经网络算法，计算原始证据体中每类数据的证据权重，所述证据权重用于区分每类数据的推荐价值；S2: Based on the original body of evidence, through radial basis function and neural network algorithm, calculate the weight of evidence for each type of data in the original body of evidence, where the weight of evidence is used to distinguish the recommendation value of each type of data;
S3：根据所述证据权重，运用D-S证据理论对原始证据体进行信息融合，以获得新的证据体；S3: According to the weight of evidence, use D-S evidence theory to fuse the original body of evidence to obtain a new body of evidence;
S4：采用功率谱估计方法对所述新的证据体进行处理，以获取推荐决策。S4: Use the power spectrum estimation method to process the new body of evidence to obtain a recommendation decision.
进一步的实施例中，步骤S1中，从多个信息源获取用户信息和对应的消费数据包括：In a further embodiment, in step S1, acquiring user information and corresponding consumption data from multiple information sources includes:
通过“昵称-手机号码”以提取用户特征数据以及用户的高频关注数据，通过“平台ID-手机号码”以从各个购物平台的数据库中挖掘用户的高频搜索数据与历史购买信息。Through "nickname-mobile phone number" to extract user characteristic data and user's high-frequency attention data, through "platform ID-mobile phone number" to mine users' high-frequency search data and historical purchase information from the databases of various shopping platforms.
进一步的实施例中，步骤S1中，对获取的用户信息和对应的消费数据进行预处理包括：In a further embodiment, in step S1, preprocessing the acquired user information and corresponding consumption data includes:
采用微格式对获取的用户信息和对应的消费数据进行表示、存储、集成和管理。The acquired user information and corresponding consumption data are represented, stored, integrated and managed using microformats.
进一步的实施例中，步骤S2中，基于所述原始证据体，通过径向基函数和神经网络算法，计算原始证据体中每类数据的证据权重的方法包括：In a further embodiment, in step S2, based on the original body of evidence, the method for calculating the weight of evidence for each type of data in the original body of evidence through radial basis functions and neural network algorithms includes:
采用径向基神经网络以计算原始证据体中每类数据的证据权重；Using radial basis neural network to calculate the evidence weight of each type of data in the original body of evidence;
所述径向基神经网络的隐藏层为径向基高斯层，对应的传递函数为高斯型函数： The hidden layer of the radial basis neural network is a radial basis Gaussian layer, and the corresponding transfer function is a Gaussian function:
所述径向基神经网络的输出层为softmax层，对应的传递函数为： The output layer of the radial basis neural network is the softmax layer, and the corresponding transfer function is:
其中，c为输出分类数目，x为神经元输入，y为神经元输出，σj为方差，j为输入个数。Among them, c is the number of output categories, x is the neuron input, y is the neuron output, σ j is the variance, and j is the number of inputs.
进一步的实施例中，步骤S3中，根据所述证据权重，运用D-S证据理论对原始证据体进行信息融合，以获得新的证据体的方法包括：In a further embodiment, in step S3, according to the weight of the evidence, using the D-S evidence theory to perform information fusion on the original body of evidence, the method for obtaining a new body of evidence includes:
根据D-S证据理论，引入证据可行度μ作为评判标准以修改原始证据体M，根据下述公式计算修改后的原始证据体M的基本概率分配值：According to the D-S evidence theory, the feasibility of evidence μ is introduced as a criterion to modify the original evidence body M, and the basic probability distribution value of the modified original evidence body M is calculated according to the following formula:
M＝[m(A1)m(A2)…m(An)m(Θ)]M=[m(A 1 )m(A 2 )...m(A n )m(Θ)]
其中， in,
根据基于局部冲突分配策略的合成规则，对修改后的原始证据体M进行融合，以获得新的证据体，采用下述公式计算融合后所得新证据体的基本概率分配值：According to the synthesis rule based on the local conflict allocation strategy, the modified original evidence body M is fused to obtain a new evidence body, and the basic probability distribution value of the new evidence body obtained after fusion is calculated by the following formula:
当时， 其中A,B,C,D表示证据，m表示证据的合成规则，j表示证据体中证据个数，Θ表示识别框架，k表示证据之间的冲突程度，M’表示修改后的证据体。when hour, Among them, A, B, C, D represent evidence, m represents the synthesis rule of evidence, j represents the number of evidence in the evidence body, Θ represents the recognition frame, k represents the degree of conflict between the evidences, and M' represents the modified evidence body.
进一步的实施例中，所述证据可行度μ的影响因子包括信息数据的时效性、稳定性和全面性中的一种或者多种。In a further embodiment, the impact factor of the evidence feasibility μ includes one or more of the timeliness, stability and comprehensiveness of the information data.
进一步的实施例中，所述方法还包括：In a further embodiment, the method further includes:
响应于每两个原始证据合成新的证据，对新的证据进行归一化处理。The new evidence is normalized in response to synthesizing a new evidence for every two original evidences.
进一步的实施例中，步骤S4中，采用功率谱估计方法对所述新的证据体进行处理，以获取推荐决策是指，In a further embodiment, in step S4, the power spectrum estimation method is used to process the new body of evidence, so as to obtain the recommendation decision means,
根据用户需求和特征信息x(n)的自相关函数所述自相关函数代表任意两个不同用户在不同时刻的用户需求和特征信息xN(n)与xN(n+m)之间的相关程度，由该相关程度计算出功率谱密度Pxx(ω)＝∑mΦxx(m)e-zωm，所述功率谱密度与相关程度为一对傅里叶变换。Autocorrelation function according to user requirements and feature information x(n) The autocorrelation function represents the correlation degree between the user requirements and feature information x N (n) and x N (n+m) of any two different users at different times, and the power spectral density P xx is calculated from the correlation degree (ω)=∑ m Φ xx (m)e -zωm , the power spectral density and the correlation degree are a pair of Fourier transforms.
基于前述方法，本发明还提及一种基于多源信息融合的移动电子商务推荐系统，所述系统包括：Based on the aforementioned method, the present invention also refers to a mobile e-commerce recommendation system based on multi-source information fusion, the system comprising:
用以从多个信息源获取用户信息和对应的消费数据，对获取的用户信息和对应的消费数据进行预处理，以获取原始证据体的模块，所述原始证据体被划分成若干类；A module for obtaining user information and corresponding consumption data from multiple information sources, and preprocessing the obtained user information and corresponding consumption data to obtain an original body of evidence, which is divided into several categories;
用以基于所述原始证据体，通过径向基函数和神经网络算法，计算原始证据体中每类数据的证据权重的模块，所述证据权重用于区分每类数据的推荐价值；A module for calculating the weight of evidence for each type of data in the original body of evidence through radial basis functions and neural network algorithms based on the original body of evidence, where the weight of evidence is used to distinguish the recommendation value of each type of data;
用以根据所述证据权重，运用D-S证据理论对原始证据体进行信息融合，以获得新的证据体的模块；A module for performing information fusion on the original body of evidence by using the D-S evidence theory according to the weight of the evidence to obtain a new body of evidence;
用以采用功率谱估计方法对所述新的证据体进行处理，以获取推荐决策的模块。A module for processing the new body of evidence using a power spectrum estimation method to obtain a recommendation decision.
以上本发明的技术方案，与现有相比，其显著的有益效果在于：The above technical scheme of the present invention, compared with the existing ones, has the following significant beneficial effects:
1)根据消费平台内外的两种类型信息，获取用户信息和数据，确保数据来源多样化。1) Obtain user information and data according to two types of information inside and outside the consumption platform, to ensure the diversification of data sources.
2)结合径向基神经网络与D-S证据理论，使用位置信息，社交平台评论，产品信息和用户信息，有效增加推荐准确性，弥补了以往推荐方法仅关注产品以及用户在消费平台的购物信息，不结合用户的其他信息的准确性缺陷；2) Combining radial basis neural network and D-S evidence theory, using location information, social platform comments, product information and user information to effectively increase the accuracy of recommendation, making up for the previous recommendation methods that only focus on products and user shopping information on consumer platforms, Not incorporating the accuracy defect of the user's other information;
3)采用可行度来修改证据体，进行信息融合，避免D-S理论的鲁棒性和一票否决性；3) Use feasibility to modify the evidence body and perform information fusion to avoid the robustness and one-vote veto of D-S theory;
4)采用可行度来修改证据体、以及根据局部冲突分配合成规则这两个方面的结合，既能提高推荐的准确性，降低推荐系统响应时间，又能增加推荐覆盖率，提高推荐服务性能。4) The combination of using feasibility to modify the evidence body and assigning synthesis rules according to local conflicts can not only improve the accuracy of recommendation, reduce the response time of the recommendation system, but also increase the coverage of recommendation and improve the performance of recommendation service.
应当理解，前述构思以及在下面更加详细地描述的额外构思的所有组合只要在这样的构思不相互矛盾的情况下都可以被视为本公开的发明主题的一部分。另外，所要求保护的主题的所有组合都被视为本公开的发明主题的一部分。It is to be understood that all combinations of the foregoing concepts, as well as additional concepts described in greater detail below, are considered to be part of the inventive subject matter of the present disclosure to the extent that such concepts are not contradictory. Additionally, all combinations of the claimed subject matter are considered to be part of the inventive subject matter of this disclosure.
结合附图从下面的描述中可以更加全面地理解本发明教导的前述和其他方面、实施例和特征。本发明的其他附加方面例如示例性实施方式的特征和/或有益效果将在下面的描述中显见，或通过根据本发明教导的具体实施方式的实践中得知。The foregoing and other aspects, embodiments and features of the present teachings can be more fully understood from the following description when taken in conjunction with the accompanying drawings. Other additional aspects of the invention, such as features and/or benefits of the exemplary embodiments, will be apparent from the description below, or learned by practice of specific embodiments in accordance with the teachings of this invention.
附图说明Description of drawings
附图不意在按比例绘制。在附图中，在各个图中示出的每个相同或近似相同的组成部分可以用相同的标号表示。为了清晰起见，在每个图中，并非每个组成部分均被标记。现在，将通过例子并参考附图来描述本发明的各个方面的实施例，其中：The drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component that is illustrated in various figures may be represented by the same reference numeral. For clarity, not every component is labeled in every figure. Embodiments of various aspects of the present invention will now be described by way of example and with reference to the accompanying drawings, wherein:
图1是本发明的基于多源信息融合的移动电子商务推荐方法的流程图。FIG. 1 is a flow chart of the mobile e-commerce recommendation method based on multi-source information fusion of the present invention.
具体实施方式Detailed ways
为了更了解本发明的技术内容，特举具体实施例并配合所附图式说明如下。In order to better understand the technical content of the present invention, specific embodiments are given and described below in conjunction with the accompanying drawings.
结合图1，本发明提出一种基于多源信息融合的移动电子商务推荐方法，所述方法包括：1, the present invention proposes a mobile e-commerce recommendation method based on multi-source information fusion, the method includes:
S1：从多个信息源获取用户信息和对应的消费数据，对获取的用户信息和对应的消费数据进行预处理，以获取原始证据体，所述原始证据体被划分成若干类。S1: Acquire user information and corresponding consumption data from multiple information sources, and preprocess the acquired user information and corresponding consumption data to obtain an original body of evidence, which is divided into several categories.
信息源包括云数据，各个购物平台的数据库，用户浏览的网页信息、视频信息，搜索引擎提供的用户数据，用户的聊天记录数据，存储在用户移动终端上的位置信息、语音、图片、视频等。Information sources include cloud data, databases of various shopping platforms, web page information and video information browsed by users, user data provided by search engines, user chat record data, location information, voice, pictures, videos, etc. stored on the user's mobile terminal .
本发明提出，优选的，从所有可能获取到用户信息的信息源来获取信息，以全面了解消费者的需求，再根据需求推荐产品。尤其是位置信息，消费者的位置与他们的购物行为之间存在密切关系，为了使推荐系统发挥更大的作用，移动电子商务推荐系统可以选择整合用户位置信息，即，将多源信息融合方法引入到位置和历史行为信息的整合中。The present invention proposes that, preferably, obtain information from all information sources that may obtain user information, so as to fully understand the needs of consumers, and then recommend products according to the needs. Especially the location information, there is a close relationship between the consumer's location and their shopping behavior. In order to make the recommendation system play a greater role, the mobile e-commerce recommendation system can choose to integrate the user's location information, that is, the multi-source information fusion method. Introduced into the integration of location and historical behavioral information.
获取方法包括以下几种：通过“昵称-手机号码”以提取用户特征数据以及用户的高频关注数据，通过“平台ID-手机号码”以从各个购物平台的数据库中挖掘用户的高频搜索数据与历史购买信息等等。The acquisition methods include the following: using "nickname-mobile phone number" to extract user characteristic data and user's high-frequency attention data, and using "platform ID-mobile phone number" to mine users' high-frequency search data from the databases of various shopping platforms with historical purchase information and more.
本发明针对移动电子商务中多源信息融合与决策推荐，使用位置信息、社交平台评论、以及产品信息和用户信息，有效增加推荐准确性。该方法弥补了以往推荐方法仅关注产品以及用户在消费平台的购物信息，不结合用户的其他信息的准确性缺陷。Aiming at multi-source information fusion and decision-making recommendation in mobile e-commerce, the present invention uses location information, social platform comments, product information and user information to effectively increase recommendation accuracy. This method makes up for the accuracy defect of previous recommendation methods that only focus on products and users' shopping information on the consumption platform, and does not combine other information of users.
进一步的实施例中，步骤S1中，对获取的用户信息和对应的消费数据进行预处理包括：In a further embodiment, in step S1, preprocessing the acquired user information and corresponding consumption data includes:
采用微格式对获取的用户信息和对应的消费数据进行表示、存储、集成和管理。The acquired user information and corresponding consumption data are represented, stored, integrated and managed using microformats.
通过对获取的用户信息和对应的消费数据进行预处理，以使获取的数据格式统一，便于用户阅读和/或机器处理。By preprocessing the acquired user information and the corresponding consumption data, the format of the acquired data is unified, which is convenient for user reading and/or machine processing.
S2：基于所述原始证据体，通过径向基函数和神经网络算法，计算原始证据体中每类数据的证据权重，所述证据权重用于区分每类数据的推荐价值。S2: Based on the original body of evidence, the radial basis function and the neural network algorithm are used to calculate the weight of evidence for each type of data in the original body of evidence, where the weight of evidence is used to distinguish the recommendation value of each type of data.
具体的，本发明通过采用一种改进的径向基神经网络以计算原始证据体中每类数据的证据权重。Specifically, the present invention uses an improved radial basis neural network to calculate the evidence weight of each type of data in the original evidence body.
所述径向基神经网络的隐藏层为径向基高斯层，对应的传递函数为高斯型函数： The hidden layer of the radial basis neural network is a radial basis Gaussian layer, and the corresponding transfer function is a Gaussian function:
所述径向基神经网络的输出层为softmax层，对应的传递函数为： The output layer of the radial basis neural network is the softmax layer, and the corresponding transfer function is:
其中，c为输出分类数目，x为神经元输入，y为神经元输出，σj为方差，j为输入个数。Among them, c is the number of output categories, x is the neuron input, y is the neuron output, σ j is the variance, and j is the number of inputs.
S3：根据所述证据权重，运用D-S证据理论对原始证据体进行信息融合，以获得新的证据体。S3: According to the weight of the evidence, use the D-S evidence theory to perform information fusion on the original body of evidence to obtain a new body of evidence.
为避免D-S理论的鲁棒性和一票否决性，基于D-S证据理论，引入证据可行度μ作为评判标准以修改原始证据体M，根据下述公式计算修改后的原始证据体M的基本概率分配值：In order to avoid the robustness and one-vote veto of the D-S theory, based on the D-S evidence theory, the feasibility of evidence μ is introduced as a criterion to modify the original body of evidence M, and the basic probability distribution of the modified original body of evidence M is calculated according to the following formula: value:
M＝[m(A1)m(A2)…m(An)m(Θ)]M=[m(A 1 )m(A 2 )...m(A n )m(Θ)]
其中， in,
优选的，所述证据可行度μ的影响因子包括信息数据的时效性、稳定性和全面性中的一种或者多种。Preferably, the impact factor of the evidence feasibility μ includes one or more of the timeliness, stability and comprehensiveness of the information data.
对原始证据体M完成修改之后，再根据基于局部冲突分配策略的合成规则，对修改后的原始证据体M进行融合，以获得新的证据体，采用下述公式计算融合后所得新证据体的基本概率分配值：After the original body of evidence M is modified, the modified original body of evidence M is fused according to the synthesis rules based on the local conflict allocation strategy to obtain a new body of evidence. The following formula is used to calculate the value of the new body of evidence obtained after fusion: Basic probability assignment values:
当时， 其中A,B,C,D表示证据，m表示证据的合成规则，j表示证据体中证据个数，Θ表示识别框架，k表示证据之间的冲突程度，M’表示修改后的证据体。when hour, Among them, A, B, C, D represent evidence, m represents the synthesis rule of evidence, j represents the number of evidence in the evidence body, Θ represents the recognition frame, k represents the degree of conflict between the evidences, and M' represents the modified evidence body.
通过采用可行度来修改证据体、以及根据局部冲突分配合成规则这两个方面的结合，既能提高推荐的准确性，降低推荐系统响应时间，又能增加推荐覆盖率。The combination of modifying the evidence body with feasibility and assigning synthesis rules according to local conflicts can not only improve the accuracy of recommendation, reduce the response time of the recommendation system, but also increase the recommendation coverage.
优选的，响应于每两个原始证据合成新的证据，对新的证据进行归一化处理，以便于后续处理。Preferably, in response to synthesizing new evidence for every two original evidences, the new evidence is normalized to facilitate subsequent processing.
S4：综合考虑信息的时效性，稳定性，全面性等众多因素，采用功率谱估计方法对所述新的证据体进行处理，以获取推荐决策。S4: Considering the timeliness, stability, comprehensiveness and other factors of the information comprehensively, the power spectrum estimation method is used to process the new body of evidence to obtain a recommendation decision.
具体的，根据用户需求和特征信息x(n)的自相关函数所述自相关函数代表任意两个不同用户在不同时刻的用户需求和特征信息xN(n)与xN(n+m)之间的相关程度，由该相关程度计算出功率谱密度Pxx(ω)＝∑mΦxx(m)e-zωm，所述功率谱密度与相关程度为一对傅里叶变换。Specifically, according to user requirements and the autocorrelation function of feature information x(n) The autocorrelation function represents the correlation degree between the user requirements and feature information x N (n) and x N (n+m) of any two different users at different times, and the power spectral density P xx is calculated from the correlation degree (ω)=∑ m Φ xx (m)e -zωm , the power spectral density and the correlation degree are a pair of Fourier transforms.
基于前述方法，本发明还提及一种基于多源信息融合的移动电子商务推荐系统，所述系统包括以下几个模块：Based on the aforementioned method, the present invention also refers to a mobile e-commerce recommendation system based on multi-source information fusion, the system includes the following modules:
1)用以从多个信息源获取用户信息和对应的消费数据，对获取的用户信息和对应的消费数据进行预处理，以获取原始证据体的模块，所述原始证据体被划分成若干类。1) A module for obtaining user information and corresponding consumption data from multiple information sources, and preprocessing the obtained user information and corresponding consumption data to obtain an original body of evidence, which is divided into several categories .
2)用以基于所述原始证据体，通过径向基函数和神经网络算法，计算原始证据体中每类数据的证据权重的模块，所述证据权重用于区分每类数据的推荐价值。2) A module for calculating the weight of evidence for each type of data in the original body of evidence through radial basis functions and neural network algorithms based on the original body of evidence, where the weight of evidence is used to distinguish the recommendation value of each type of data.
3)用以根据所述证据权重，运用D-S证据理论对原始证据体进行信息融合，以获得新的证据体的模块。3) A module for performing information fusion on the original body of evidence by using the D-S evidence theory according to the weight of the evidence to obtain a new body of evidence.
4)用以采用功率谱估计方法对所述新的证据体进行处理，以获取推荐决策的模块。4) A module for processing the new body of evidence using a power spectrum estimation method to obtain a recommendation decision.
在本公开中参照附图来描述本发明的各方面，附图中示出了许多说明的实施例。本公开的实施例不必定义在包括本发明的所有方面。应当理解，上面介绍的多种构思和实施例，以及下面更加详细地描述的那些构思和实施方式可以以很多方式中任意一种来实施，这是因为本发明所公开的构思和实施例并不限于任何实施方式。另外，本发明公开的一些方面可以单独使用，或者与本发明公开的其他方面的任何适当组合来使用。Aspects of the invention are described in this disclosure with reference to the accompanying drawings, in which a number of illustrative embodiments are shown. Embodiments of the present disclosure are not necessarily defined to include all aspects of the invention. It should be understood that the various concepts and embodiments described above, as well as those described in greater detail below, can be implemented in any of a number of ways, as the concepts and embodiments disclosed herein do not limited to any implementation. Additionally, some aspects of the present disclosure may be used alone or in any suitable combination with other aspects of the present disclosure.
虽然本发明已以较佳实施例揭露如上，然其并非用以限定本发明。本发明所属技术领域中具有通常知识者，在不脱离本发明的精神和范围内，当可作各种的更动与润饰。因此，本发明的保护范围当视权利要求书所界定者为准。Although the present invention has been disclosed above with preferred embodiments, it is not intended to limit the present invention. Those skilled in the art to which the present invention pertains can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention should be determined according to the claims.
Claims (9)
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910030517.8A CN109785064A (en) | 2019-01-14 | 2019-01-14 | A kind of mobile e-business recommended method and system based on Multi-source Information Fusion |
| PCT/CN2019/092977 WO2020147265A1 (en) | 2019-01-14 | 2019-06-26 | Mobile electronic commerce recommendation method and system employing multisource information fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910030517.8A CN109785064A (en) | 2019-01-14 | 2019-01-14 | A kind of mobile e-business recommended method and system based on Multi-source Information Fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109785064A true CN109785064A (en) | 2019-05-21 |
Family
ID=66500468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910030517.8A Pending CN109785064A (en) | 2019-01-14 | 2019-01-14 | A kind of mobile e-business recommended method and system based on Multi-source Information Fusion |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109785064A (en) |
| WO (1) | WO2020147265A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348964A (en) * | 2019-07-09 | 2019-10-18 | 葛晓滨 | It is a kind of based on the wisdom electronic commerce recommending method more perceived |
| WO2020147265A1 (en) * | 2019-01-14 | 2020-07-23 | 南京信息工程大学 | Mobile electronic commerce recommendation method and system employing multisource information fusion |
| CN112800999A (en) * | 2021-02-04 | 2021-05-14 | 大连大学 | Intelligent control system target identification fusion method based on intelligent networking |
| CN112989207A (en) * | 2021-04-27 | 2021-06-18 | 武汉卓尔数字传媒科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN113988060A (en) * | 2021-08-31 | 2022-01-28 | 中国电子科技集团公司第十五研究所 | Data information recommendation method and device, terminal equipment and storage medium |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113051249A (en) * | 2021-03-22 | 2021-06-29 | 江苏杰瑞信息科技有限公司 | Cloud service platform design method based on multi-source heterogeneous big data fusion |
| CN115225301B (en) * | 2021-04-21 | 2023-11-21 | 上海交通大学 | Hybrid intrusion detection method and system based on D-S evidence theory |
| CN113609360B (en) * | 2021-08-19 | 2024-07-05 | 武汉东湖大数据科技股份有限公司 | Method and system based on scenerization multi-source data fusion analysis |
| CN113792805B (en) * | 2021-09-16 | 2024-05-10 | 河北工程大学 | Water quality evaluation method based on multi-source data fusion |
| CN114492594A (en) * | 2021-12-30 | 2022-05-13 | 中国航空研究院 | Multi-sensor attribute identification method for multi-domain combat |
| CN114757295B (en) * | 2022-04-28 | 2024-04-02 | 浙江科技学院 | Multi-sensor data fusion method and application based on cloud model and evidence theory |
| CN114997339B (en) * | 2022-08-01 | 2023-05-12 | 白杨时代(北京)科技有限公司 | Multi-source target intelligent decision method and related device |
| CN117150440B (en) * | 2023-11-01 | 2024-02-06 | 人民法院信息技术服务中心 | A multi-source information fusion method and device based on information uncertainty |
| CN117828527A (en) * | 2023-12-29 | 2024-04-05 | 中国空间技术研究院 | Multi-source data fusion and situation generation method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103064856A (en) * | 2011-10-21 | 2013-04-24 | 中国移动通信集团重庆有限公司 | Resource recommendation method and device based on belief network |
| US20140244429A1 (en) * | 2013-02-28 | 2014-08-28 | Lg Electronics Inc. | Apparatus and method for processing a multimedia commerce service |
| US20170236183A1 (en) * | 2016-02-11 | 2017-08-17 | Ebay Inc. | System and method for detecting visually similar items |
| CN107909433A (en) * | 2017-11-14 | 2018-04-13 | 重庆邮电大学 | A kind of Method of Commodity Recommendation based on big data mobile e-business |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6922680B2 (en) * | 2002-03-19 | 2005-07-26 | Koninklijke Philips Electronics N.V. | Method and apparatus for recommending an item of interest using a radial basis function to fuse a plurality of recommendation scores |
| CN103544539A (en) * | 2013-10-12 | 2014-01-29 | 国家电网公司 | Method for predicting variables of users on basis of artificial neural networks and D-S (Dempster-Shafer) evidence theory |
| US9535897B2 (en) * | 2013-12-20 | 2017-01-03 | Google Inc. | Content recommendation system using a neural network language model |
| CN106327240A (en) * | 2016-08-11 | 2017-01-11 | 中国船舶重工集团公司第七0九研究所 | Recommendation method and recommendation system based on GRU neural network |
| CN107341447A (en) * | 2017-06-13 | 2017-11-10 | 华南理工大学 | A kind of face verification mechanism based on depth convolutional neural networks and evidence k nearest neighbor |
| CN109146644A (en) * | 2018-09-05 | 2019-01-04 | 广州小楠科技有限公司 | A kind of e-commerce system |
| CN109785064A (en) * | 2019-01-14 | 2019-05-21 | 南京信息工程大学 | A kind of mobile e-business recommended method and system based on Multi-source Information Fusion |
-
2019
- 2019-01-14 CN CN201910030517.8A patent/CN109785064A/en active Pending
- 2019-06-26 WO PCT/CN2019/092977 patent/WO2020147265A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103064856A (en) * | 2011-10-21 | 2013-04-24 | 中国移动通信集团重庆有限公司 | Resource recommendation method and device based on belief network |
| US20140244429A1 (en) * | 2013-02-28 | 2014-08-28 | Lg Electronics Inc. | Apparatus and method for processing a multimedia commerce service |
| US20170236183A1 (en) * | 2016-02-11 | 2017-08-17 | Ebay Inc. | System and method for detecting visually similar items |
| CN107909433A (en) * | 2017-11-14 | 2018-04-13 | 重庆邮电大学 | A kind of Method of Commodity Recommendation based on big data mobile e-business |
Non-Patent Citations (1)
| Title |
|---|
| 郭艳: "面向移动电子商务的个性化推荐策略研究", 《万方数据库》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020147265A1 (en) * | 2019-01-14 | 2020-07-23 | 南京信息工程大学 | Mobile electronic commerce recommendation method and system employing multisource information fusion |
| CN110348964A (en) * | 2019-07-09 | 2019-10-18 | 葛晓滨 | It is a kind of based on the wisdom electronic commerce recommending method more perceived |
| CN112800999A (en) * | 2021-02-04 | 2021-05-14 | 大连大学 | Intelligent control system target identification fusion method based on intelligent networking |
| CN112800999B (en) * | 2021-02-04 | 2023-12-01 | 大连大学 | Intelligent command and control system target recognition fusion method based on the Internet of Intelligence |
| CN112989207A (en) * | 2021-04-27 | 2021-06-18 | 武汉卓尔数字传媒科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN113988060A (en) * | 2021-08-31 | 2022-01-28 | 中国电子科技集团公司第十五研究所 | Data information recommendation method and device, terminal equipment and storage medium |
| CN113988060B (en) * | 2021-08-31 | 2024-09-17 | 中国电子科技集团公司第十五研究所 | Data information recommendation method, device, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020147265A1 (en) | 2020-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020147265A1 (en) | Mobile electronic commerce recommendation method and system employing multisource information fusion | |
| Goyani et al. | A review of movie recommendation system: Limitations, Survey and Challenges | |
| Wang et al. | A dnn-based cross-domain recommender system for alleviating cold-start problem in e-commerce | |
| Zhang et al. | An associative classification-based recommendation system for personalization in B2C e-commerce applications | |
| US20210035183A1 (en) | Method and system for a recommendation engine utilizing progressive labeling and user content enrichment | |
| Dhingra et al. | Spam analysis of big reviews dataset using Fuzzy Ranking Evaluation Algorithm and Hadoop | |
| Jain et al. | Movie recommendation system: hybrid information filtering system | |
| CN111475744B (en) | Personalized position recommendation method based on ensemble learning | |
| TWI705411B (en) | Method and device for identifying users with social business characteristics | |
| CN108876536A (en) | Collaborative filtering recommending method based on arest neighbors information | |
| Li et al. | Social recommendation based on trust and influence in SNS environments | |
| Patil et al. | Social context-aware and fuzzy preference temporal graph for personalized B2B marketing campaigns recommendations | |
| Patro et al. | Knowledge-based preference learning model for recommender system using adaptive neuro-fuzzy inference system | |
| Elahi et al. | Recommender systems: Challenges and opportunities in the age of big data and artificial intelligence | |
| Lee et al. | A hybrid collaborative filtering-based product recommender system using search keywords | |
| Wu et al. | A federated deep learning framework for privacy-preserving consumer electronics recommendations | |
| Latrech et al. | CoDFi-DL: a hybrid recommender system combining enhanced collaborative and demographic filtering based on deep learning | |
| Rahim et al. | An efficient recommender system algorithm using trust data | |
| Sun | Music individualization recommendation system based on big data analysis | |
| Li et al. | An attention mechanism and residual network based knowledge graph-enhanced recommender system | |
| CN114936901A (en) | Visual perception recommendation method and system based on cross-modal semantic reasoning and fusion | |
| Pasricha et al. | A new approach for book recommendation using opinion leader mining | |
| Zhang | Intelligent recommendation model of contemporary pop music based on knowledge map | |
| Drif et al. | Context-awareness in ensemble recommender system framework | |
| Wasid et al. | Context similarity measurement based on genetic algorithm for improved recommendations |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190521 |
|
| RJ01 | Rejection of invention patent application after publication |