Parameter influence degree analysis method, device, electronic device and storage medium
By using the pre-constructed knowledge graph to determine the degree of influence of the parameters to be analyzed on the platform to be analyzed, the problem of strong subjective factors in the analysis results in the prior art is solved, and the accuracy and efficiency of the analysis are improved.
Patent Information
- Application Number
- CN202111537116.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-13
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-12-13
AI Technical Summary
In the prior art, the analysis results of the recommended platform are subjectively factors and have low accuracy based on the empirical value.
By obtaining the parameters to be analyzed and the information of the platform to be analyzed, the target knowledge relationship chain is determined using the pre-constructed knowledge graph, the association relationship between adjacent entities is obtained, and the degree of influence of the parameters to be analyzed on the platform to be analyzed is determined based on the association relationship.
Without manual participation, the degree of influence of the parameters to be analyzed on the platform to be analyzed is determined directly based on the pre-constructed knowledge graph, which improves the efficiency and accuracy of determining the degree of influence.
Smart Images

Figure CN114201555B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data analysis technology, and in particular to a parameter influence degree analysis method, device, electronic device and storage medium. Background Art
[0002] At present, we are looking for influencing factors on the recommendation platforms in each industry, and then using these influencing factors to analyze the impact on the recommendation platforms, so as to facilitate accurate delivery of the recommendation platforms.
[0003] In the related art, when analyzing the impact of influencing factors on the recommendation platform, relevant personnel often set them based on experience values, but the results obtained have strong subjective factors and the accuracy of the results is not high. Summary of the invention
[0004] The present application provides a parameter influence degree analysis method, device, electronic device and storage medium to solve the problem in the prior art that the influence of influencing factors on the recommendation platform is analyzed according to the settings based on empirical values, but the obtained analysis results have strong subjective factors and low accuracy.
[0005] In a first aspect, an embodiment of the present application provides a parameter influence degree analysis method, comprising:
[0006] Obtain the parameters to be analyzed and the platform information to be analyzed;
[0007] According to a pre-constructed knowledge graph, a target knowledge relationship chain formed by the parameter to be analyzed and the platform information to be analyzed is determined; the knowledge graph is a knowledge graph containing a correspondence between parameters and platform information, and the target knowledge relationship chain indicates a relationship between the parameter to be analyzed and the platform information to be analyzed in the knowledge graph;
[0008] According to the knowledge graph, obtaining the association relationship between each adjacent entity in the target knowledge relationship chain;
[0009] According to each of the association relationships, the degree of influence of the parameter to be analyzed on the platform to be analyzed is determined.
[0010] Optionally, determining the target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed according to the pre-built knowledge graph includes:
[0011] Extracting at least one knowledge relationship chain from the parameter to be analyzed to the platform information to be analyzed from the knowledge graph;
[0012] Determine, in the at least one knowledge relationship chain, the knowledge relationship chain with the least number of entities as the target knowledge relationship chain.
[0013] Optionally, determining, according to each of the association relationships, the degree of influence of the parameter to be analyzed on the platform to be analyzed includes:
[0014] Determine a first association relationship in a preset relationship mapping table that satisfies a preset condition with the association relationship;
[0015] According to the relationship mapping table, obtaining the degree of association corresponding to each of the first association relationships;
[0016] According to each of the correlation degrees, the influence degree of the parameter to be analyzed on the platform to be analyzed is determined, and the correlation degree is positively correlated with the influence degree.
[0017] Optionally, the determining of a first association relationship in a preset relationship mapping table that satisfies a preset condition with the association relationship includes:
[0018] Calculating the similarity between each of the association relationships and each second association relationship in the preset relationship mapping table;
[0019] The second association relationship with the greatest similarity is determined as the first association relationship.
[0020] Optionally, determining the influence degree of the parameter to be analyzed on the platform to be analyzed according to each of the correlation degrees includes:
[0021] The product of each of the correlation degrees is calculated, and the product is used as the influence degree.
[0022] Optionally, the platform information to be analyzed includes the name of the platform to be analyzed and the application field of the platform to be analyzed; the pre-built knowledge graph includes a first knowledge graph and a second knowledge graph, the first knowledge graph is a knowledge graph containing the correspondence between fields and parameters, and the second knowledge graph is a knowledge graph containing the correspondence between fields and platform names;
[0023] The step of determining the target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed according to the pre-built knowledge graph includes:
[0024] Determine, according to the first knowledge graph, a first knowledge relationship chain formed between the parameter to be analyzed and the application field of the platform to be analyzed;
[0025] Determine, according to the second knowledge graph, a second knowledge relationship chain formed by the name of the platform to be analyzed and the application field of the platform to be analyzed;
[0026] A knowledge relationship chain formed by the first knowledge relationship chain and the second knowledge relationship chain is determined as the target knowledge relationship chain.
[0027] Optionally, the process of constructing the knowledge graph includes:
[0028] Acquire a corpus, the corpus comprising at least one text corpus and at least one attribute information corresponding to each of the text corpus, the text corpus comprising at least one of a parameter and platform information;
[0029] Segmenting each text corpus in the corpus to obtain at least one vocabulary word;
[0030] Identifying entities in the vocabulary and determining relationships between entities;
[0031] Using at least one attribute information corresponding to each of the text corpora as an attribute of a corresponding entity;
[0032] A knowledge graph corresponding to the corpus is constructed based on entities, the association relationships between the entities, and the attributes of each entity.
[0033] In a second aspect, an embodiment of the present application provides a parameter influence degree analysis device, comprising:
[0034] The first acquisition module is used to acquire the parameters to be analyzed and the platform information to be analyzed;
[0035] A first determination module is used to determine a target knowledge relationship chain formed by the parameter to be analyzed and the platform information to be analyzed according to a pre-constructed knowledge graph; the knowledge graph is a knowledge graph containing a correspondence between parameters and platform information, and the target knowledge relationship chain indicates a relationship between the parameter to be analyzed and the platform information to be analyzed in the knowledge graph;
[0036] A second acquisition module is used to acquire the association relationship between each adjacent entity in the target knowledge relationship chain according to the knowledge graph;
[0037] The second determination module is used to determine the influence degree of the parameter to be analyzed on the platform to be analyzed according to each of the association relationships.
[0038] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; the memory is used to store a computer program;
[0039] The processor is used to execute the program stored in the memory to implement the parameter influence degree analysis method described in the first aspect.
[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the parameter influence degree analysis method described in the first aspect.
[0041] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art: the method provided by the embodiment of the present application, by obtaining the parameters to be analyzed and the platform information to be analyzed; according to the pre-constructed knowledge graph, the target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed is determined; the knowledge graph is a knowledge graph containing the corresponding relationship between the parameters and the platform information, and the target knowledge relationship chain indicates the relationship between the parameters to be analyzed and the platform information to be analyzed in the knowledge graph; according to the knowledge graph, the association relationship between each adjacent entity in the target knowledge relationship chain is obtained; according to each association relationship, the influence degree of the parameters to be analyzed on the platform to be analyzed is determined. In this way, when it is necessary to determine the influence degree of the parameters to be analyzed on the platform to be analyzed, the target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed is first determined through the pre-constructed knowledge graph, and then the association relationship between each two adjacent entities in the knowledge relationship chain is obtained from the knowledge graph, so that the influence degree of the parameters to be analyzed on the platform to be analyzed is determined according to the association relationship. Without manual participation, the influence degree of the parameters to be analyzed on the platform to be analyzed can be directly determined based on the pre-constructed knowledge graph, which improves the efficiency of determining the influence degree. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0044] Figure 1 An application scenario diagram of the parameter influence degree analysis method provided in one embodiment of the present application;
[0045] Figure 2 A flow chart of a parameter influence degree analysis method provided in one embodiment of the present application;
[0046] Figure 3 A structural diagram of a parameter influence degree analysis device provided in one embodiment of the present application;
[0047] Figure 4 A structural diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0049] Before further describing the embodiments of the present invention in detail, the nouns and terms involved in the embodiments of the present invention are described. The nouns and terms involved in the embodiments of the present invention are subject to the following explanations.
[0050] Knowledge graph: The knowledge graph aims to describe various entities or concepts and their relationships that exist in the real world. It constitutes a huge semantic network graph, where nodes represent entities or concepts and edges are composed of attributes or relationships.
[0051] Entity: An entity refers to something that is distinguishable and exists independently, such as a person's name, a city name, a plant name, a product name, a field name, a platform name, etc. Entity is the most basic element in a knowledge graph. There are different relationships between different entities. For example, in a certain knowledge graph, Zhang San and Li Si are a couple, and both Zhang San and Li Si are entities.
[0052] Association relationship: In the knowledge graph, the edge represents the association relationship in the knowledge graph, which is used to identify a certain connection between different entities. For example, in a certain knowledge graph, Zhang San and Li Si are husband and wife, where husband and wife is the association relationship between the two.
[0053] Attributes: Entities and relationships in the knowledge graph can have their own attributes. From an entity to its attribute value, different attribute types correspond to edges of different types of attributes. Attributes mainly refer to the characteristic information of the object. For example, "area", "population", and "capital" are several different attributes. Attribute values mainly refer to the values of the attributes, such as 9.6 million square kilometers.
[0054] According to an embodiment of the present application, a parameter influence degree analysis method is provided. Optionally, in the embodiment of the present application, the above parameter influence degree analysis method can be applied to Figure 1 In the hardware environment composed of the terminal 101 and the server 102 shown in FIG. Figure 1 As shown, the server 102 is connected to the terminal 101 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 102. The above-mentioned network includes but is not limited to: a wide area network, a metropolitan area network or a local area network, and the terminal 101 is not limited to a PC, a mobile phone, a tablet computer, etc.
[0055] The parameter influence degree analysis method of the embodiment of the present application can be executed by the server 102, or by the terminal 101, or by both the server 102 and the terminal 101. The terminal 101 executes the parameter influence degree analysis method of the embodiment of the present application, or the client installed thereon.
[0056] Taking the server executing the parameter influence degree analysis method of the embodiment of the present application as an example, Figure 2 is a flow chart of an optional parameter influence degree analysis method according to an embodiment of the present application, such as Figure 2 As shown, the process of the method may include the following steps:
[0057] Step 201: Obtain parameters to be analyzed and platform information to be analyzed.
[0058] In some embodiments, the parameters to be analyzed and the platform information to be analyzed may be input by relevant personnel through a display interface of the server, or may be selected from options on the display interface.
[0059] The parameters to be analyzed and the platform information to be analyzed can be set by relevant personnel according to actual needs. For example, if the platform to be analyzed is a data recommendation platform, the parameters to be analyzed can be region, price, season, and applicable population, etc., and the platform information to be analyzed can be the name of the platform to be analyzed (such as food recommendation platform, shopping recommendation platform, etc.) and the application field of the platform to be analyzed (such as food field, shopping field, etc.).
[0060] Step 202: Determine the target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed based on the pre-constructed knowledge graph.
[0061] In some embodiments, the pre-constructed knowledge graph may be a knowledge graph related to parameters and / or platform information. When the knowledge graph includes parameters and / or platform information, the target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed may be determined based on the knowledge graph.
[0062] Among them, due to the intricate connections between the entities in the knowledge graph, there may be more than one knowledge relationship chain from the parameters to be analyzed to the platform information to be analyzed. Therefore, it is necessary to determine the target knowledge relationship chain that can better express the relationship between the parameters to be analyzed and the platform information to be analyzed from multiple knowledge relationship chains.
[0063] In an optional embodiment, determining a target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed according to a pre-built knowledge graph includes:
[0064] Extract at least one knowledge relationship chain from the parameter to be analyzed to the platform information to be analyzed from the knowledge graph; determine the knowledge relationship chain with the least number of entities in the at least one knowledge relationship chain as the target knowledge relationship chain.
[0065] In some embodiments, the parameters to be analyzed and the platform information to be analyzed can be input into the knowledge graph and the two can be taken as entities. The locations of the parameters to be analyzed and the platform information to be analyzed can be queried in the knowledge graph, so as to determine at least one knowledge relationship chain formed from the parameters to be analyzed to the platform information to be analyzed based on the locations of the parameters to be analyzed and the platform information to be analyzed in the knowledge graph. For different knowledge relationship chains, the number of entities may be different. Therefore, by comparing the number of entities in different knowledge relationship chains, the knowledge relationship chain with the least number of entities is taken as the target knowledge relationship chain.
[0066] It can be understood that when the platform information to be analyzed is the name of the platform to be analyzed, the pre-constructed knowledge graph can be a knowledge graph of parameters and platform names, and the target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed can be directly obtained from the knowledge graph.
[0067] In an optional embodiment, the platform information to be analyzed includes the name of the platform to be analyzed and the application field of the platform to be analyzed; the pre-constructed knowledge graph includes a first knowledge graph and a second knowledge graph, the first knowledge graph is a knowledge graph including the correspondence between the field and the parameter, and the second knowledge graph is a knowledge graph including the correspondence between the field and the platform name;
[0068] According to the pre-built knowledge graph, determine the target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed, including:
[0069] According to the first knowledge graph, determine the first knowledge relationship chain formed by the parameters to be analyzed and the application field of the platform to be analyzed; according to the second knowledge graph, determine the second knowledge relationship chain formed by the name of the platform to be analyzed and the application field of the platform to be analyzed; determine the knowledge relationship chain formed by the first knowledge relationship chain and the second knowledge relationship chain as the target knowledge relationship chain.
[0070] It can be understood that when there is already a first knowledge graph of parameters and intermediate parameters (such as fields) and a second knowledge graph of intermediate parameters and platform names, the first knowledge graph and the second knowledge graph can be directly used to determine the target knowledge relationship chain without reconstructing the knowledge graph with parameters and platform names, which saves the knowledge graph construction process and improves the efficiency of determining the degree of impact.
[0071] Specifically, when the knowledge graph includes the first knowledge graph and the second knowledge graph, the information of the platform to be analyzed obtained includes the name of the platform to be analyzed and the application field of the platform to be analyzed, so that the first knowledge relationship chain formed by the parameters to be analyzed and the application field of the platform to be analyzed is queried from the first knowledge graph, and the second knowledge relationship chain formed by the name of the platform to be analyzed and the application field of the platform to be analyzed is queried from the second knowledge graph, and further, the first knowledge relationship chain and the second knowledge relationship chain are merged to obtain the target knowledge relationship chain.
[0072] The specific implementation method for determining the first knowledge relationship chain and the second knowledge relationship chain may refer to the above-mentioned related embodiments and will not be described in detail here.
[0073] There are many ways to construct a knowledge graph, and you can refer to the construction methods in related technologies.
[0074] In an optional embodiment, the process of constructing a knowledge graph includes:
[0075] A corpus is obtained, the corpus includes at least one text corpus and at least one attribute information corresponding to each text corpus, the text corpus includes at least one of parameters and platform information; each text corpus in the corpus is segmented to obtain at least one vocabulary; entities in the vocabulary are identified, and associations between entities are constructed; at least one attribute information corresponding to each text corpus is used as an attribute of a corresponding entity; and a knowledge graph corresponding to the corpus is constructed according to the entities, the associations between entities, and the attributes of each entity.
[0076] In some embodiments, the text corpus is a text of a certain length, and its source is not limited here, such as news text, user input text, converted text recognized by voice input, and any other text that conforms to the content of the knowledge graph.
[0077] After the text corpus is segmented, the obtained words can be compared with a preset entity set to determine the entities in the text corpus. Alternatively, different means such as a preset model analysis method (for example, based on a hidden Markov model, a conditional random field or a recurrent neural network model) can be used to identify entities.
[0078] After the entity is confirmed, feature extraction can be performed on the text information in the text corpus except for the entity, and the extracted features can be used as association relationships.
[0079] Furthermore, after determining the entity, the relationship and the attribute of the entity, the knowledge graph can be constructed based on these three, and then the degree of influence can be determined.
[0080] Step 203: According to the knowledge graph, obtain the association relationship between each adjacent entity in the target knowledge relationship chain.
[0081] In some embodiments, the knowledge graph includes entities, relationships between entities, and attributes of entities and relationships. After determining the target knowledge relationship chain, the corresponding relationship can be obtained from the knowledge graph based on the target knowledge relationship chain.
[0082] Step 204: Determine the influence of the parameter to be analyzed on the platform to be analyzed according to each association relationship.
[0083] In some embodiments, after determining the association relationship between entities in the target knowledge relationship chain, the association degree between adjacent entities can be determined by semantic analysis, and then the influence of the parameter to be analyzed on the platform to be analyzed can be further determined based on the association degree.
[0084] However, since semantic analysis is performed on every two adjacent entities, the amount of calculation of the server will increase. Therefore, the present application provides the following embodiments for determining the degree of influence.
[0085] In an optional embodiment, determining the influence of the parameter to be analyzed on the platform to be analyzed according to each association relationship includes:
[0086] Determine a first association relationship in a preset relationship mapping table that satisfies a preset condition with the association relationship; obtain the degree of association corresponding to each first association relationship according to the relationship mapping table; determine the degree of influence of the parameter to be analyzed on the platform to be analyzed according to each degree of association, and the degree of association is positively correlated with the degree of influence.
[0087] In some embodiments, after the knowledge graph is constructed, all the associations in the knowledge graph can be extracted first, and similar or identical associations can be classified into the same group by classifying the associations, and the same association degree can be configured for the associations in each classification result, thereby obtaining a relationship mapping table. Alternatively, after the associations are classified, a new association is determined for each classification result as a representative of all associations in the classification result, and the association degree is configured for the new association to obtain a relationship mapping table.
[0088] Therefore, the relationship mapping table is a table of association relationships and association degrees.
[0089] By pre-constructing a relationship mapping table, after obtaining the association relationship, the association relationship is compared with the second association relationship stored in the relationship mapping table. If it is determined that the association relationship satisfies the first association relationship of the preset condition in the relationship mapping table, the correlation degree corresponding to the first association relationship is obtained, and then the influence of the parameter to be analyzed on the platform to be analyzed is calculated according to the correlation degree.
[0090] In an optional embodiment, determining a first association relationship that satisfies a preset condition in a preset relationship mapping table for each association relationship includes:
[0091] The similarity between each association relationship and the second association relationship in the preset relationship mapping table is calculated; and the second association relationship with the greatest similarity is determined as the first association relationship.
[0092] In some embodiments, by calculating the similarity between the association relationship and each second association relationship in the relationship mapping table and comparing the similarities calculated for the association relationships, the maximum value of the similarities is determined, and the second association relationship with the maximum similarity is used as the first association relationship.
[0093] In an optional embodiment, after the correlation degrees are obtained, the correlation degrees may be multiplied, and the obtained product may be used as the influence of the parameter to be analyzed on the platform to be analyzed.
[0094] The value range of the correlation degree may be, but is not limited to, 0 to 1.
[0095] In a specific embodiment, taking the parameter to be analyzed as region, and the platform information to be analyzed as field and recommendation platform as an example, by constructing a knowledge graph between the region and different fields, and a knowledge graph between the recommendation platform and different fields, etc., according to the relational characteristics of the knowledge graph, the degree of relationship between any two of them can be known.
[0096] Since it is necessary to determine the influence relationship between the target region and the target recommendation platform, and the relationship between the two is relatively simple in the knowledge graph, perhaps one or two layers, while some relationships are relatively complex, and may require more than ten layers or even dozens of layers to find, thus forming a relationship chain (that is, the target knowledge relationship chain mentioned above), and then through semantic understanding, each relationship in the corresponding relationship chain (that is, the association relationship mentioned above) is parsed into a relationship statement existing in the preset relationship mapping table.
[0097] Among them, the relationship mapping table is a mapping between the relationship statements between two entities in the aforementioned knowledge graph and the corresponding relationship impact quantification.
[0098] For example, if region and food are strongly correlated, the mapped proportion will be relatively high, for example, it may be 90%; shopping or online shopping is weakly correlated with region, which may be 10%. Through the relationship mapping table, the obtained relationship chain is mapped to obtain a mapped data chain, and the data in this data chain is multiplied (because it is multiplied because of the layer-by-layer association), and finally the influence coefficient of the region on the corresponding recommendation platform is obtained.
[0099] For example, we need to determine the influence of the region on the food recommendation platform. First, we need to obtain the relationship chain: region - ① - food field - ② - food recommendation platform; ① is the correlation between the region and the food field, which is highly correlated, 90% in the relationship mapping table, and ② the food field and the food recommendation platform are completely correlated, 100% in the relationship mapping table, so the final influence is the product of 90% and 100%, that is, 90%.
[0100] The parameter influence degree analysis method in this embodiment obtains the relationship chain between region and recommendation system through the knowledge graph constructed by region-related, recommendation system-related and different fields, and obtains the final influence degree of region on recommendation system through semantic understanding and relationship proportion mapping.
[0101] Based on the same concept, a parameter influence degree analysis device is provided in the embodiment of the present application. The specific implementation of the device can be found in the description of the method embodiment part, and the repeated parts will not be repeated. Figure 3 As shown, the device mainly includes:
[0102] The first acquisition module 301 is used to acquire the parameters to be analyzed and the platform information to be analyzed;
[0103] The first determination module 302 is used to determine the target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed according to the pre-constructed knowledge graph; the knowledge graph is a knowledge graph containing the corresponding relationship between the parameters and the platform information, and the target knowledge relationship chain indicates the relationship between the parameters to be analyzed and the platform information to be analyzed in the knowledge graph;
[0104] The second acquisition module 303 is used to acquire the association relationship between each adjacent entity in the target knowledge relationship chain according to the knowledge graph;
[0105] The second determination module 304 is used to determine the influence of the parameter to be analyzed on the platform to be analyzed according to each association relationship.
[0106] Based on the same concept, an electronic device is also provided in the embodiment of the present application, such as Figure 4 As shown, the electronic device mainly includes: a processor 401, a memory 402 and a communication bus 403, wherein the processor 401 and the memory 402 communicate with each other through the communication bus 403. The memory 402 stores a program that can be executed by the processor 401, and the processor 401 executes the program stored in the memory 402 to implement the following steps:
[0107] Obtain the parameters to be analyzed and the platform information to be analyzed;
[0108] According to the pre-constructed knowledge graph, a target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed is determined; the knowledge graph is a knowledge graph containing the corresponding relationship between the parameters and the platform information, and the target knowledge relationship chain indicates the relationship between the parameters to be analyzed and the platform information to be analyzed in the knowledge graph;
[0109] According to the knowledge graph, obtain the association relationship between each adjacent entity in the target knowledge relationship chain;
[0110] According to each association relationship, the influence degree of the parameter to be analyzed on the platform to be analyzed is determined.
[0111] The communication bus 403 mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 403 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0112] The memory 402 may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Alternatively, the memory may also be at least one storage device located away from the processor 401.
[0113] The above-mentioned processor 401 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., and can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
[0114] In another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program runs on a computer, the computer executes the parameter influence degree analysis method described in the above embodiment.
[0115] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instruction is loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instruction can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instruction is transmitted from a website site, a computer, a server or a data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, a data center, etc. that contains one or more available media integration. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape, etc.), an optical medium (such as a DVD) or a semiconductor medium (such as a solid-state hard disk), etc.
[0116] It should be noted that, in this article, the association terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual association or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0117] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A parameter influence degree analysis method, characterized in that: include: Obtaining parameters to be analyzed and information of platforms to be analyzed, wherein the parameters to be analyzed include region, price, season, and applicable population, and the platforms to be analyzed include a food recommendation platform or a shopping recommendation platform; Determine, according to the pre-built knowledge graph, a target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed; The knowledge graph is a knowledge graph containing the correspondence between parameters and platform information, and the target knowledge relationship chain indicates the relationship between the parameters to be analyzed and the platform information to be analyzed in the knowledge graph; According to the knowledge graph, obtaining the association relationship between each adjacent entity in the target knowledge relationship chain; Determining, according to each of the association relationships, the degree of influence of the parameter to be analyzed on the platform to be analyzed; The process of constructing the knowledge graph includes: Acquire a corpus, the corpus comprising at least one text corpus and at least one attribute information corresponding to each of the text corpus, the text corpus comprising at least one of a parameter and platform information; Segmenting each text corpus in the corpus to obtain at least one vocabulary word; Identifying entities in the vocabulary and determining relationships between entities; Using at least one attribute information corresponding to each of the text corpora as an attribute of a corresponding entity; A knowledge graph corresponding to the corpus is constructed based on entities, the association relationships between the entities, and the attributes of each entity.
2. The parameter influence degree analysis method according to claim 1, characterized in that: The step of determining the target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed according to the pre-built knowledge graph includes: Extracting at least one knowledge relationship chain from the parameter to be analyzed to the platform information to be analyzed from the knowledge graph; Determine, in the at least one knowledge relationship chain, the knowledge relationship chain with the least number of entities as the target knowledge relationship chain.
3. The parameter influence degree analysis method according to claim 1, characterized in that: Determining the influence of the parameter to be analyzed on the platform to be analyzed according to each of the association relationships includes: Determine a first association relationship in a preset relationship mapping table that satisfies a preset condition with the association relationship; According to the relationship mapping table, obtaining the degree of association corresponding to each of the first association relationships; According to each of the correlation degrees, the influence degree of the parameter to be analyzed on the platform to be analyzed is determined, and the correlation degree is positively correlated with the influence degree.
4. The parameter influence degree analysis method according to claim 3 is characterized in that: The first association relationship in the preset relationship mapping table that satisfies the preset condition with the association relationship includes: Calculating the similarity between each of the association relationships and each second association relationship in the preset relationship mapping table; The second association relationship with the greatest similarity is determined as the first association relationship.
5. The parameter influence degree analysis method according to claim 3, characterized in that: Determining the influence of the parameter to be analyzed on the platform to be analyzed according to each of the correlation degrees includes: The product of each of the correlation degrees is calculated, and the product is used as the influence degree.
6. The parameter influence degree analysis method according to claim 1, characterized in that: The platform information to be analyzed includes the name of the platform to be analyzed and the application field of the platform to be analyzed; the pre-built knowledge graph includes a first knowledge graph and a second knowledge graph, the first knowledge graph is a knowledge graph containing the correspondence between fields and parameters, and the second knowledge graph is a knowledge graph containing the correspondence between fields and platform names; The step of determining the target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed according to the pre-built knowledge graph includes: Determine, according to the first knowledge graph, a first knowledge relationship chain formed between the parameter to be analyzed and the application field of the platform to be analyzed; Determine, according to the second knowledge graph, a second knowledge relationship chain formed by the name of the platform to be analyzed and the application field of the platform to be analyzed; A knowledge relationship chain formed by the first knowledge relationship chain and the second knowledge relationship chain is determined as the target knowledge relationship chain.
7. A parameter influence degree analysis device, characterized in that: include: The first acquisition module is used to acquire parameters to be analyzed and information of platforms to be analyzed, wherein the parameters to be analyzed include region, price, season and applicable population, and the platforms to be analyzed include food recommendation platforms or shopping recommendation platforms; A first determination module is used to determine a target knowledge relationship chain formed by the parameters to be analyzed and the platform information to be analyzed according to a pre-built knowledge graph; The knowledge graph is a knowledge graph containing the correspondence between parameters and platform information, and the target knowledge relationship chain indicates the relationship between the parameters to be analyzed and the platform information to be analyzed in the knowledge graph; A second acquisition module is used to acquire the association relationship between each adjacent entity in the target knowledge relationship chain according to the knowledge graph; A second determination module is used to determine the influence degree of the parameter to be analyzed on the platform to be analyzed according to each of the association relationships; The process of constructing the knowledge graph includes: Acquire a corpus, the corpus comprising at least one text corpus and at least one attribute information corresponding to each of the text corpus, the text corpus comprising at least one of a parameter and platform information; Segmenting each text corpus in the corpus to obtain at least one vocabulary word; Identifying entities in the vocabulary and determining relationships between entities; Using at least one attribute information corresponding to each of the text corpora as an attribute of a corresponding entity; A knowledge graph corresponding to the corpus is constructed based on entities, the association relationships between the entities, and the attributes of each entity.
8. An electronic device, characterized in that: include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor is used to execute the program stored in the memory to implement the parameter influence degree analysis method described in any one of claims 1-6.
9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the parameter influence degree analysis method according to any one of claims 1 to 6 is implemented.
