A method and device for determining the similarity of a first product to a second product

Abstract

The purpose of the present application is to provide a method and device for determining the similarity between a first product and a second product. Compared with the prior art, the present application determines the first common user set corresponding to the first product and the competitor of the first product, and the second common user set corresponding to the second product and the competitor of the second product; converts the first common user set and the second common user set into a first weight vector and a second weight vector respectively; determines the first decentralization adjustment factor corresponding to the first weight vector and the second decentralization adjustment factor corresponding to the second weight vector; based on the similarity between the first weight vector and the second weight vector, the first decentralization adjustment factor and the second decentralization adjustment factor, the weight of the second product in the first weight vector and the weight of the first product in the second weight vector, determines the similarity between the first product and the second product. In this way, the influence of the arrangement order of the competing products on the similarity calculation result is eliminated.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a technology for determining the similarity between a first product and a second product. Background Art

[0002] Competitive product analysis is a specific scenario for calculating similarity and is often used in the product development process. However, unlike similarity calculations such as text analysis, word order is also one of the similarity measurement criteria when performing text analysis. Texts composed of the same keywords in different orders have different similarities. However, for competitive product analysis, different rankings of the same competitor should not cause differences in similarity. However, in actual application scenarios, existing competitive product analysis methods ignore the impact of competitor order on similarity, resulting in different competitor rankings having a greater impact on the results of competitive product analysis. Therefore, a similarity determination method applied to similar fields such as competitive product analysis is needed to achieve the purpose of avoiding the influence of order factors on the similarity calculation results. Summary of the invention

[0003] The purpose of this application is to provide a method and device for determining the similarity between a first product and a second product.

[0004] According to one aspect of the present application, a method for determining a similarity between a first product and a second product is provided, wherein the method comprises:

[0005] Determine a first common user set corresponding to a first product and a competitor of the first product, and a second common user set corresponding to a second product and a competitor of the second product, wherein the elements in the first common user set are the number of common users of the first product and the competitor of the first product, and the elements in the second common user set are the number of common users of the second product and the competitor of the second product, wherein the competitor of the first product includes the second product and the competitor of the second product includes the first product;

[0006] Convert the first common user set and the second common user set into a first weight vector and a second weight vector respectively, wherein each component in the first weight vector represents the weight of each competitor of the first product in the first common user set, and each component in the second weight vector represents the weight of each competitor of the second product in the second common user set;

[0007] Determine a first decentralization adjustment factor corresponding to the first weight vector and a second decentralization adjustment factor corresponding to the second weight vector, wherein the first decentralization adjustment factor is determined based on the position of the weights of the common competitors of the first product and the second product in the first weight vector, the total number of components of the first weight vector, the number of common competitors of the first product and the second product, and the center position of the first weight vector, and the second decentralization adjustment factor is determined based on the position of the weights of the common competitors of the first product and the second product in the second weight vector, the total number of components of the second weight vector, the number of common competitors of the first product and the second product, and the center position of the second weight vector;

[0008] Based on the similarity between the first weight vector and the second weight vector, the first decentralization adjustment factor and the second decentralization adjustment factor, the weight of the second product in the first weight vector and the weight of the first product in the second weight vector, the similarity of the first product to the second product is determined.

[0009] Furthermore, the converting the first common user set and the second common user set into a first weight vector and a second weight vector respectively comprises:

[0010] performing a normalization operation on the number of common users in the first common user set and the second common user set to convert the number of common users in the first common user set and the second common user set into corresponding weights;

[0011] The weight corresponding to the number of common users in the first common user set and the weight corresponding to the number of common users in the second common user set are respectively used as components to form a first weight vector and a second weight vector.

[0012] Furthermore, the specific calculation formulas of the first decentralization adjustment factor corresponding to the first weight vector and the second decentralization adjustment factor corresponding to the second weight vector include:

[0013] in, and Corresponding to the first weight vector and the second weight vector respectively, Corresponding to the first decentralization adjustment factor, Corresponding to the second decentralization adjustment factor, The position of the weight of the common competitor of the first product and the second product in the first weight vector, The number of common competitors for the first and second products. as well as Corresponding to the center position of the first weight vector and the center position of the second weight vector respectively, and They correspond to the total number of components of the first weight vector and the total number of components of the second weight vector respectively.

[0014] Furthermore, the calculation formula for the similarity between the first product and the second product includes:

[0015] Among them, A and B correspond to the first product and the second product respectively, sim(A,B) corresponds to the similarity between the first product and the second product, Corresponding to the similarity between the first weight vector and the second weight vector, w AB corresponds to the weight of the first product in the second weight vector, Corresponding to the second decentralization adjustment factor, w BA corresponds to the weight of the second product in the first weight vector, Corresponding to the first decentralization adjustment factor.

[0016] Further, wherein the The calculation methods include: cosine similarity, Jaccard coefficient, Pearson correlation coefficient, Minkowski distance, Manhattan distance or Eucledian distance.

[0017] Preferably, after converting the first common user set and the second common user set into a first weight vector and a second weight vector respectively, the method further includes: setting the weights of the first product and the second product to 1, and adding them to the first weight vector and the second weight vector respectively.

[0018] According to another aspect of the present application, a computer-readable medium is provided, on which computer-readable instructions are stored. The computer-readable instructions can be executed by a processor to implement the operations of the aforementioned method.

[0019] According to another aspect of the present application, a device for determining a similarity between a first product and a second product is provided, wherein the device comprises:

[0020] one or more processors; and

[0021] A memory storing computer readable instructions which, when executed, cause the processor to perform the operations of the above-described method.

[0022] Compared with the prior art, the present application determines the first common user set corresponding to the first product and the competitor of the first product, and the second common user set corresponding to the second product and the competitor of the second product; converts the first common user set and the second common user set into the first weight vector and the second weight vector respectively; determines the first decentralization adjustment factor corresponding to the first weight vector and the second decentralization adjustment factor corresponding to the second weight vector; and determines the similarity between the first product and the second product based on the similarity between the first weight vector and the second weight vector, the first decentralization adjustment factor and the second decentralization adjustment factor, the weight of the second product in the first weight vector, and the weight of the first product in the second weight vector. In this way, the influence of the arrangement order of the competitors on the similarity calculation results is eliminated, so that the conclusion of the competitor analysis conforms to the actual application scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0024] Figure 1 A flow chart of a method for determining a similarity between a first product and a second product according to one aspect of the present application is shown;

[0025] Figure 2 A flow chart of a method for determining the similarity between a first product and a second product according to a preferred embodiment of the present application is shown.

[0026] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION

[0027] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0028] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (CPU), input / output interfaces, network interfaces and memories.

[0029] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0030] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0031] In order to further explain the technical means adopted by the present application and the effects achieved, the technical solution of the present application is clearly and completely described below in combination with the accompanying drawings and preferred embodiments.

[0032] Figure 1 A method for determining the similarity between a first product and a second product provided by one aspect of the present application is shown, wherein the method comprises:

[0033] S11 determines a first common user set corresponding to a first product and a competitor of the first product, and a second common user set corresponding to a second product and a competitor of the second product, wherein the elements in the first common user set are the number of common users of the first product and the competitor of the first product, and the elements in the second common user set are the number of common users of the second product and the competitor of the second product, wherein the competitor of the first product includes the second product and the competitor of the second product includes the first product;

[0034] S12 converts the first common user set and the second common user set into a first weight vector and a second weight vector respectively, wherein each component in the first weight vector represents the weight of each competitor of the first product in the first common user set, and each component in the second weight vector represents the weight of each competitor of the second product in the second common user set;

[0035] S13 determines a first decentralization adjustment factor corresponding to the first weight vector and a second decentralization adjustment factor corresponding to the second weight vector, wherein the first decentralization adjustment factor is determined based on the position of the weight of the common competitors of the first product and the second product in the first weight vector, the total number of components of the first weight vector, the number of common competitors of the first product and the second product, and the center position of the first weight vector, and the second decentralization adjustment factor is determined based on the position of the weight of the common competitors of the first product and the second product in the second weight vector, the total number of components of the second weight vector, the number of common competitors of the first product and the second product, and the center position of the second weight vector;

[0036] S14 determines the similarity of the first product to the second product based on the similarity between the first weight vector and the second weight vector, the first decentralization adjustment factor and the second decentralization adjustment factor, the weight of the second product in the first weight vector and the weight of the first product in the second weight vector.

[0037] In this embodiment, in step S11, a first common user set corresponding to the first product and its competitors, and a second common user set corresponding to the second product and its competitors are determined, wherein the elements in the first common user set are the number of common users between the first product and its competitors, and the elements in the second common user set are the number of common users between the second product and its competitors, wherein the competitors of the first product include the second product and the competitors of the second product include the first product.

[0038] Here, the first product and the second product are usually similar products that constitute a competitive relationship, that is, they are competing products. At the same time, the first product and the second product have their own competing products. In this step, the number of common users of the first product and its various competing products (including the second product) is counted, and the number of common users corresponding to each competing product is used as each element of the first common user set; the number of common users of the second product and its various competing products (including the first product) is counted, and the number of common users corresponding to each competing product is used as each element of the second common user set. It should be clear that although the first product and the second product are competing products, their respective competing products do not necessarily overlap. Taking Taobao as the first product and Douyin as the second product as an example, when Taobao, an online shopping product, is analyzed for competing products, since Douyin also has the function of online shopping, Douyin can constitute a competing product of Taobao; but when Douyin is analyzed for competing products, video products such as Bilibili can constitute Douyin's competing products, but will not constitute Taobao's competing products.

[0039] Based on the above description, an example is given below: the first product is A, and its competitors include B, C, and D, and the number of common users between A and B is 30, the number of common users between A and C is 20, and the number of common users between A and D is 10; the second product is B, and its competitors include D, E, F, G, and A, and the number of common users between B and D is 70, the number of common users between B and E is 60, the number of common users between B and F is 50, the number of common users between B and G is 40, and the number of common users between B and A is 30. Therefore, the first common user set is {30, 20, 10}; the second common user set is {70, 60, 50, 40, 30}.

[0040] In this embodiment, in step S12, the first common user set and the second common user set are converted into a first weight vector and a second weight vector, respectively, wherein each component in the first weight vector represents the weight of each competitor of the first product in the first common user set, and each component in the second weight vector represents the weight of each competitor of the second product in the second common user set.

[0041] In this step, in order to quantify the influence of the first product's competitor on the first product, and the influence of the second product's competitor on the second product, each competitor is regarded as an indicator and a weight is determined for each indicator. Here, the specific method of weight determination is not limited to a description, and the applicable weight determination methods include but are not limited to normalization, entropy weight method, coefficient of variation method, CRITIC method, principal component analysis method, factor analysis method, etc.

[0042] Further, here, taking the normalized weight determination method as an example, the converting of the first common user set and the second common user set into the first weight vector and the second weight vector respectively includes: performing a normalization operation on the number of common users in the first common user set and the second common user set to convert the number of common users in the first common user set and the second common user set into corresponding weights; and taking the weights corresponding to the number of common users in the first common user set and the weights corresponding to the number of common users in the second common user set as components to form the first weight vector and the second weight vector.

[0043] Continuing with the above example, the first common user set is {30, 20, 10}, which is normalized to obtain the first weight vector To quantify the impact of the first product's competitors on the first product; the second common user set is {70, 60, 50, 40, 30}, which is normalized to obtain the second weight vector To quantify the impact of the first product’s competitors on the first product.

[0044] In a preferred embodiment, see Figure 2As shown, Figure 2 Steps S21, S22, S24 and S25 in Figure 1 Steps S11, S12, S13 and S14 in the embodiment are the same or substantially the same, and are therefore not described in detail herein, but are included herein by reference. Step S23 is: after converting the first common user set and the second common user set into a first weight vector and a second weight vector respectively, the weights of the first product and the second product are set to 1, and are added to the first weight vector and the second weight vector respectively.

[0045] Here, since the degree of mutual influence between products is different, for example, users who use the Mushroom House app with a smaller audience are very likely to also use Taobao, but among users who use Taobao, the proportion of users who also use Mushroom House is low. Therefore, the degree of influence of Taobao on Mushroom House is greater than the degree of influence of Mushroom House on Taobao. However, if the similarity is calculated only based on other competing products that do not include itself, the similarity of the first product to the second product is the same as the similarity of the second product to the first product. Therefore, the product itself is introduced as its own competitor, and the weight is set to 1. Through this method, on the one hand, the influence of the product on itself is introduced, and on the other hand, the difference in the degree of mutual influence between products is achieved, making the results of competitive product analysis more in line with the actual situation.

[0046] In this embodiment, in the step S13 / S24, a first decentralization adjustment factor corresponding to the first weight vector and a second decentralization adjustment factor corresponding to the second weight vector are determined, wherein the first decentralization adjustment factor is determined based on the position of the weights of the common competitors of the first product and the second product in the first weight vector, the total number of components of the first weight vector, the number of common competitors of the first product and the second product, and the center position of the first weight vector, and the second decentralization adjustment factor is determined based on the position of the weights of the common competitors of the first product and the second product in the second weight vector, the total number of components of the second weight vector, the number of common competitors of the first product and the second product, and the center position of the second weight vector.

[0047] Furthermore, specific calculation formulas for the first decentralization adjustment factor corresponding to the first weight vector and the second decentralization adjustment factor corresponding to the second weight vector include: in, and Corresponding to the first weight vector and the second weight vector respectively, Corresponding to the first decentralization adjustment factor, Corresponding to the second decentralization adjustment factor, The position of the weight of the common competitor of the first product and the second product in the first weight vector, The number of common competitors for the first and second products. as well as Corresponding to the center position of the first weight vector and the center position of the second weight vector respectively, and They correspond to the total number of components of the first weight vector and the total number of components of the second weight vector respectively.

[0048] In this step, since the position of the corresponding weights of the competitors in the weight vector will affect the calculation results of the similarity, and in actual application scenarios, the order of competitors should be irrelevant to the results of the competitor analysis, a decentralization factor is set. The specific function of the decentralization factor is to make the similarities calculated with different weight orders the same, thereby eliminating the influence of the order of the corresponding weights of competitors on the results of the competitor analysis.

[0049] In this embodiment, in step S14 / S25, the similarity between the first product and the second product is determined based on the similarity between the first weight vector and the second weight vector, the first decentralization adjustment factor and the second decentralization adjustment factor, the weight of the second product in the first weight vector and the weight of the first product in the second weight vector.

[0050] Furthermore, the calculation formula for the similarity between the first product and the second product includes: Among them, A and B correspond to the first product and the second product respectively, sim(A,B) corresponds to the similarity between the first product and the second product, Corresponding to the similarity between the first weight vector and the second weight vector, w AB corresponds to the weight of the first product in the second weight vector, Corresponding to the second decentralization adjustment factor, w BA corresponds to the weight of the second product in the first weight vector, Corresponding to the first decentralization adjustment factor.

[0051] Furthermore, the The calculation methods include: cosine similarity, Jaccard coefficient, Pearson correlation coefficient, Minkowski distance, Manhattan distance or Eucledian distance. Here, no restrictive description is given to the specific calculation method of weight vector similarity, and any method that can calculate vector similarity is within the protection scope of this application.

[0052] Here, the first weight vector and the second weight vector For example, by using cosine similarity and the calculation method designed in this application, it is found that the similarity between the first product and the second product is about 0.181. This method can determine the similarity between the first product and the second product, and because the decentralization factor is introduced, the order of the competing products of the first product and / or the second product will not affect the calculation result of the similarity, so that the result of the competitive product analysis conforms to the actual application scenario.

[0053] Compared with the prior art, the present application determines the first common user set corresponding to the first product and the competitor of the first product, and the second common user set corresponding to the second product and the competitor of the second product; converts the first common user set and the second common user set into the first weight vector and the second weight vector respectively; determines the first decentralization adjustment factor corresponding to the first weight vector and the second decentralization adjustment factor corresponding to the second weight vector; and determines the similarity between the first product and the second product based on the similarity between the first weight vector and the second weight vector, the first decentralization adjustment factor and the second decentralization adjustment factor, the weight of the second product in the first weight vector, and the weight of the first product in the second weight vector. In this way, the influence of the arrangement order of the competitors on the similarity calculation result is eliminated.

[0054] In addition, an embodiment of the present application also provides a computer-readable medium on which computer-readable instructions are stored, and the computer-readable instructions can be executed by a processor to implement the aforementioned method.

[0055] The embodiment of the present application further provides a device for determining a similarity between a first product and a second product, wherein the device includes:

[0056] one or more processors; and

[0057] A memory storing computer readable instructions which, when executed, cause the processor to perform the operations of the aforementioned method.

[0058] For example, when the computer-readable instructions are executed, the one or more processors: determine a first set of common users corresponding to a first product and a competitor of the first product, and a second set of common users corresponding to a second product and a competitor of the second product; convert the first set of common users and the second set of common users into a first weight vector and a second weight vector, respectively; determine a first decentralization adjustment factor corresponding to the first weight vector and a second decentralization adjustment factor corresponding to the second weight vector; determine the similarity between the first product and the second product based on the similarity between the first weight vector and the second weight vector, the first decentralization adjustment factor and the second decentralization adjustment factor, the weight of the second product in the first weight vector, and the weight of the first product in the second weight vector.

[0059] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for determining a similarity between a first product and a second product, in, The method comprises: Determine a first common user set corresponding to a first product and a competitor of the first product, and a second common user set corresponding to a second product and a competitor of the second product, wherein the elements in the first common user set are the number of common users of the first product and the competitor of the first product, and the elements in the second common user set are the number of common users of the second product and the competitor of the second product, wherein the competitor of the first product includes the second product and the competitor of the second product includes the first product; Convert the first common user set and the second common user set into a first weight vector and a second weight vector respectively, wherein each component in the first weight vector represents the weight of each competitor of the first product in the first common user set, and each component in the second weight vector represents the weight of each competitor of the second product in the second common user set; Determine a first decentralization adjustment factor corresponding to the first weight vector and a second decentralization adjustment factor corresponding to the second weight vector, wherein the first decentralization adjustment factor is determined based on the position of the weights of the common competitors of the first product and the second product in the first weight vector, the total number of components of the first weight vector, the number of common competitors of the first product and the second product, and the center position of the first weight vector, and the second decentralization adjustment factor is determined based on the position of the weights of the common competitors of the first product and the second product in the second weight vector, the total number of components of the second weight vector, the number of common competitors of the first product and the second product, and the center position of the second weight vector; Based on the similarity between the first weight vector and the second weight vector, the first decentralization adjustment factor and the second decentralization adjustment factor, the weight of the second product in the first weight vector and the weight of the first product in the second weight vector, the similarity of the first product to the second product is determined.

2. The method according to claim 1, in, The converting the first common user set and the second common user set into a first weight vector and a second weight vector respectively comprises: performing a normalization operation on the number of common users in the first common user set and the second common user set to convert the number of common users in the first common user set and the second common user set into corresponding weights; The weight corresponding to the number of common users in the first common user set and the weight corresponding to the number of common users in the second common user set are respectively used as components to form a first weight vector and a second weight vector.

3. The method according to claim 1 or 2, in, The specific calculation formulas of the first decentralization adjustment factor corresponding to the first weight vector and the second decentralization adjustment factor corresponding to the second weight vector include: in, and Corresponding to the first weight vector and the second weight vector respectively, Corresponding to the first decentralization adjustment factor, Corresponding to the second decentralization adjustment factor, The position of the weight of the common competitor of the first product and the second product in the first weight vector, The number of common competitors for the first and second products. as well as Corresponding to the center position of the first weight vector and the center position of the second weight vector respectively, and They correspond to the total number of components of the first weight vector and the total number of components of the second weight vector respectively.

4. The method according to claim 3, in, The calculation formula for the similarity between the first product and the second product includes: Among them, A and B correspond to the first product and the second product respectively, sim(A,B) corresponds to the similarity between the first product and the second product, Corresponding to the similarity between the first weight vector and the second weight vector, w AB corresponds to the weight of the first product in the second weight vector, Corresponding to the second decentralization adjustment factor, w BA corresponds to the weight of the second product in the first weight vector, Corresponding to the first decentralization adjustment factor.

5. The method according to claim 4, in, Said The calculation methods include: cosine similarity, Jaccard coefficient, Pearson correlation coefficient, Minkowski distance, Manhattan distance or Eucledian distance.

6. The method according to any one of claims 2 to 5, in, After converting the first common user set and the second common user set into the first weight vector and the second weight vector respectively, the method further includes: setting the weights of the first product and the second product to 1, and adding them to the first weight vector and the second weight vector respectively.

7. A computer-readable medium having computer-readable instructions stored thereon, wherein the computer-readable instructions can be executed by a processor to implement the method according to any one of claims 1 to 6.

8. A device for determining a similarity between a first product and a second product, in, The equipment includes: one or more processors; and A memory storing computer readable instructions which, when executed, cause the processor to perform the operations of the method as claimed in any one of claims 1 to 6.

Images