Customized Cooperation Invitation Intelligent Generation System and Method

Abstract

The present invention relates to the technical field of new media anchor invitations, and in particular to a customized cooperation invitation intelligent generation system and method. The method includes: obtaining new media anchor profile information and historical product promotion information, analyzing to obtain a new media anchor tag set, analyzing the historical product promotion information to obtain historical products and historical product information tag sets of each historical product; calculating the proportion values of each element in the new media anchor tag set; taking the reciprocal of the proportion value of each element as the weight value of each element, and generating information similarity values of each reference new media anchor in the new media anchor database based on the weight values; generating similarity; calculating the final matching degree according to the similarity set of each reference new media anchor and the information similarity value; using the invitation success email corresponding to the email product tag set with the highest similarity of the reference new media anchor with the highest matching degree as the reference email. This application has the effects of improving the attractiveness of email content and the invitation success rate.

Description

Technical Field

[0001] The present invention relates to the technical field of new media anchor invitation, and in particular to a customized cooperation invitation intelligent generation system and method. Background Art

[0002] With the rapid development of Internet technology, especially the rise of social media and e-commerce platforms, new media anchor marketing has become one of the important means of brand promotion and product marketing. With its huge supporter base and unique influence, new media anchors can effectively promote product sales and bring significant exposure and market feedback to the brand.

[0003] Traditional new media anchor invitation methods often rely on manual screening and judgment, which is not only inefficient, but also difficult to accurately assess the fit between new media anchors and brands. Due to the lack of attractiveness of new media anchors' email content, the email signing success rate is often not high. Therefore, how to improve the success rate of selected new media anchors receiving emails has become an urgent problem to be solved. Summary of the invention

[0004] In order to increase the attractiveness of email content and improve the success rate of invitations, this application provides a customized cooperation invitation intelligent generation system and method.

[0005] The above-mentioned invention objective of the present application is achieved through the following technical solutions:

[0006] A customized cooperation invitation intelligent generation method, comprising:

[0007] Obtain new media anchor profile information and historical product information of the new media anchor to be invited, analyze the new media anchor profile information to obtain a new media anchor tag set, analyze the historical product information to obtain historical products and historical product information tag sets of each historical product;

[0008] The number of occurrences of each element in the new media anchor tag set in the reference new media anchor tag set is counted in the new media anchor database, and the proportion of each element in the new media anchor tag set is calculated based on the number of occurrences of each element in the new media anchor tag set in the reference new media anchor tag set; the new media anchor database stores reference new media anchors with successful historical invitations and corresponding reference new media anchor tag sets, as well as successful invitation emails of the reference new media anchors and email product tag sets corresponding to the successful invitation emails;

[0009] The inverse of the proportion of each element is used as the weight value of each element, and based on the weight value, the information similarity value of each reference new media anchor in the new media anchor database is generated;

[0010] Generate the similarity between the email product tag sets of each reference new media host and the historical product promotion information tag set of the to-be-invited new media host;

[0011] Calculate the final matching degree according to the similarity set and information similarity value of each reference new media host;

[0012] Use the invitation success email corresponding to the email product tag set with the highest similarity of the reference new media host with the highest matching degree as the reference email.

[0013] In a preferred example, the present application can be further configured to: generate the information similarity value of each reference new media host in the new media host database based on the weight value, including:

[0014] Calculate the sum of the weight values of the same elements in the reference new media host tag set of the reference new media host and the new media host tag set of the to-be-invited new media host as the information similarity value of the reference new media host.

[0015] In a preferred example, the present application can be further configured to: calculate the similarity between the email product tag sets of each reference new media host and the historical product promotion information tag set of the to-be-invited new media host, including:

[0016] Calculate the sub-similarity between each email product tag set of the reference new media host and each historical product promotion information tag set of the to-be-invited new media host to obtain the sub-similarity set of the reference new media host;

[0017] Derive the first interval based on the maximum value of the sub-similarities in the sub-similarity sets of different reference new media hosts;

[0018] Calculate the proportion of the number of elements in the sub-similarity set of the reference new media host that are in the first interval to the total number of elements in the sub-similarity set to obtain the proportion value of the reference new media host;

[0019] Calculate the average value of the elements in the sub-similarity set of the reference new media host that are in the first interval;

[0020] Calculate the similarity of the reference new media host based on the proportion value and the average value.

[0021] In a preferred example, the present application can be further configured to: calculate the final matching degree according to the similarity set and information similarity value of each reference new media host, including:

[0022] Use the product of the similarity and the information similarity value as the final matching degree.

[0023] The above another object of the present invention of the application is achieved by the following technical solutions:

[0024] A customized cooperation invitation intelligent generation system for the customized cooperation invitation intelligent generation method described in any one of the above, comprising:

[0025] An information acquisition module, configured to acquire the new media anchor profile information and historical product promotion information of the new media anchor to be invited, analyze the new media anchor profile information to obtain a new media anchor tag set, and analyze the historical product promotion information to obtain historical products and historical product information tag sets of each historical product;

[0026] A proportion calculation module, configured to count the occurrence times of each element in the new media anchor tag set in a reference new media anchor tag set in the new media anchor database, and calculate the proportion value of each element in the new media anchor tag set based on the occurrence times of each element in the reference new media anchor tag set; the new media anchor database stores historical invited successful reference new media anchors and corresponding reference new media anchor tag sets, as well as the invitation successful emails of the reference new media anchors and the email product tag sets corresponding to the invitation successful emails;

[0027] An information similarity value generation module, configured to use the reciprocal of the proportion value of each element as the weight value of each element, and generate the information similarity value of each reference new media anchor in the new media anchor database based on the weight value;

[0028] A similarity calculation module, configured to generate the similarity between the email product tag set of each reference new media anchor and the historical product information tag set of the new media anchor to be invited;

[0029] A final matching degree calculation module, configured to calculate the final matching degree according to the similarity set of each reference new media anchor and the information similarity value;

[0030] An email selection module, configured to use the invitation successful email corresponding to the email product tag set with the highest similarity of the reference new media anchor with the highest matching degree as the reference email.

[0031] In a preferred example of the present application, it can be further configured that: the information similarity value generation module includes:

[0032] An information similarity value calculation sub-unit, configured to calculate the sum of the weight values of the same elements in the reference new media anchor tag set of the reference new media anchor and the new media anchor tag set of the new media anchor to be invited as the information similarity value of the reference new media anchor.

[0033] In a preferred example of the present application, it can be further configured that: the similarity calculation module includes:

[0034] A sub - similarity calculation unit, configured to calculate the sub - similarity between each email product tag set of a reference new media host and each historical product promotion information tag set of the new media host to be invited, so as to obtain a sub - similarity set of the reference new media host;

[0035] A first interval obtaining unit, configured to obtain a first interval based on the maximum value of the sub - similarities in the sub - similarity sets of different reference new media hosts;

[0036] A proportion value calculation unit, configured to calculate the proportion of the number of elements in the sub - similarity set of the reference new media host that are within the first interval to the total number of elements in the sub - similarity set, so as to obtain the proportion value of the reference new media host;

[0037] An average value calculation unit, configured to calculate the average value of the elements in the sub - similarity set of the reference new media host that are within the first interval;

[0038] A similarity calculation unit, configured to calculate the similarity of the reference new media host based on the proportion value and the average value.

[0039] In a preferred example of the present application, it can be further configured that: the final matching degree calculation module further includes: a sub - matching degree calculation unit, configured to use the product of the similarity and the information similarity value as the final matching degree.

[0040] In summary, the present application includes at least one of the following beneficial technical effects:

[0041] 1. By comprehensively considering the proportion of products with high sub - similarities among the products associated with the successful emails of the reference new media host, the similarity between the email product tag set of the reference new media host and the historical product promotion information tag set of the new media host to be invited, and the information similarity value between the reference new media host and the new media host to be invited, and emphasizing the influence of relatively niche new media host tags in terms of the information similarity value between the reference new media host and the new media host to be invited, it is possible to more comprehensively screen out the appropriate emails that truly match the new media host to be invited, improving the interest and invitation success rate of the new media host to be invited.

[0042] 2. By using the terms in the region - invited successful emails as supplementary terms and providing them to the reference emails, it is convenient for subsequent personnel to adjust and supplement the content of the reference emails as needed, and send more suitable and complete emails to the new media host, improving the invitation success rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a flowchart of the implementation of a customized cooperation invitation intelligent generation method in an embodiment of the present application;

[0044] Figure 2 is a specific implementation flowchart of step S4 of the customized cooperation invitation intelligent generation method in an embodiment of the present application;

[0045] Figure 3 It is a module connection diagram of the intelligent generation system for customized cooperation invitations in an embodiment of the present application. Specific embodiments

[0046] The exemplary embodiments of the present application will be described below with reference to the accompanying drawings. Various details of the embodiments of the present application are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted below.

[0047] It should be noted that the terms "first", "second", etc. in the present invention are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure.

[0048] In addition, the term "and / or" herein merely describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0049] The intelligent generation system and method for customized cooperation invitations of the present application will be described below with reference to the drawings.

[0050] Figure 1 It is a flowchart of the implementation of the intelligent generation method for customized cooperation invitations in an embodiment of the present application. As Figure 1 shown, the intelligent generation method for customized cooperation invitations includes:

[0051] S1. Obtain the new media anchor information and historical product promotion information of the new media anchor to be invited, analyze the new media anchor information to obtain the new media anchor tag set, and analyze the historical product promotion information to obtain the historical products and the historical product information tag sets of each historical product.

[0052] After the system receives the basic information of the new media anchor to be invited, such as xxx new media anchor / xxx blogger, online name / name, photo / avatar, active platform, etc., based on this basic information, it ensures that the crawling behavior complies with relevant laws, regulations and platform regulations. It uses crawling tools such as the requests library, Selenium library, and BeautifulSoup library of Python to crawl the name or description of the product with goods, the product purchase link or the link to the details page on the corresponding platform or website, the username or URL of the specific new media anchor, parses the page HTML or JSON data, and extracts the new media anchor profile information; accesses the posting or product promotion record page of the new media anchor, parses the page data, and extracts the relevant information of each product with goods; stores the crawled data in a local file or database, and performs data cleaning, such as removing duplicate data, handling missing values, converting data types, etc., for subsequent analysis and processing.

[0053] In addition, in addition to obtaining through crawling, it is also possible to query the new media anchor profile information and historical product promotion information of the new media anchor to be invited by directly purchasing the corresponding database or data assets.

[0054] The elements in the new media anchor label set can include domain labels, audience characteristic labels, influence labels, style labels, geographical labels, brand cooperation labels, growth trajectory labels, social image labels, content form labels, etc. Domain labels such as beauty, travel, technology, etc., audience characteristic labels such as young women, technology enthusiasts, etc., influence labels such as high interaction rate, strong supporter stickiness, etc., style labels such as humorous, professional and rigorous, approachable and down-to-earth, etc. Through inference by a pre-trained new media anchor label analysis model, the new media anchor label model is obtained through the following training method:

[0055] Perform annotation processing on each new media anchor profile sample in the new media anchor profile sample training set to label the new media anchor labels of each new media anchor profile, and the new media anchor labels are associated with all or part of the information in the new media anchor profile sample; and through the annotated new media anchor profile sample training set, train the neural network to obtain the new media anchor label model. It can be understood that for different labels, different new media anchor label models can also be trained separately for inference.

[0056] The historical product information tag set of historical product promotion information can include the category tag of the product, the category to which the product belongs, the unique selling points or features of the product, the main target audience of the product, the occasions or environments suitable for the product, etc. Among them, the category to which the product belongs, such as beauty, clothing, home, food, the unique selling points or features of the product, such as innovative design, material, function, etc., the main target audience of the product, such as young people, women, housewives, etc., the occasions or environments suitable for the product, such as home, travel, office, etc.

[0057] Similarly, through inference by a pre-trained product label analysis model, the product label analysis model is trained in the following way:

[0058] Perform annotation processing on each historical product promotion information sample in the historical product promotion information training set to label the historical product promotion information label of each historical product promotion information, and the historical product promotion information label is associated with all or part of the information in the historical product promotion information sample; and train a neural network through the annotated historical product promotion information sample training set to obtain a historical product promotion information model. It can be understood that for different labels, different product label analysis models can also be trained separately for inference.

[0059] S2. Statistically count the number of occurrences of each element in the new media anchor label set in the reference new media anchor label set in the new media anchor database, and calculate the proportion value of each element in the new media anchor label set based on the number of occurrences of each element in the reference new media anchor label set.

[0060] Among them, the new media anchor database stores the reference new media anchors with successful historical invitations and the corresponding reference new media anchor label sets, as well as the invitation successful emails of the reference new media anchors and the email product label sets corresponding to the invitation successful emails.

[0061] Specifically, the data stored in the new media anchor database can be directly processed and used by purchasing a professional industry database, or can be obtained through the same legal web crawling method as described above and then subjected to data cleaning, integration and analysis.

[0062] Similarly, the email product label set of the product associated with the email can also be obtained through the aforementioned product label analysis model.

[0063] It can be understood that after obtaining the new media anchor tag set through analysis, the occurrence times of each new media anchor tag in the new media anchor tag set are counted based on the new media anchor database. That is, there are a large number of reference new media anchor tag sets in the new media anchor database. Each time a tag appears in a reference new media anchor tag set, it is counted as one. In this way, the occurrence times of each new media anchor tag in the new media anchor tag set are counted. For example, if a new media anchor tag "technology enthusiast" appears in 38 reference new media anchor tag sets, the occurrence times is 38. The proportion value of each element in the new media anchor tag set is calculated based on the occurrence times of each element in the reference new media anchor tag set. It means that the ratio of the occurrence times of a certain element to the total occurrence times of all elements in the new media anchor tag set is the proportion value of this element. If the total occurrence times of all elements in a new media anchor tag set, for example, is 503, then the proportion of the new media anchor tag "technology enthusiast" is the ratio of 38 to 503.

[0064] S3. Take the reciprocal of the proportion value of each element as the weight value of each element, and generate the information similarity value of each reference new media anchor in the new media anchor database based on the weight value.

[0065] Continuing with the above example, the proportion of the new media anchor tag "technology enthusiast" is the ratio of 38 to 503, then the weight value of the new media anchor tag "technology enthusiast" is the ratio of 503 to 38, that is, 13.24. This step focuses on considering the influence of relatively niche new media anchor tags. That is, the smaller the new media anchor tag, the greater the weight value of this new media anchor tag.

[0066] Generating the information similarity value of each reference new media anchor in the new media anchor database based on the weight value includes:

[0067] Calculate the sum of the weight values of the same elements in the reference new media anchor tag set of the reference new media anchor and the new media anchor tag set of the to-be-invited new media anchor as the information similarity value of this reference new media anchor. The information similarity values of each reference new media anchor are obtained in turn. For example, if there are 3 same elements in the reference new media anchor tag set of a reference new media anchor and the new media anchor tag set of the to-be-invited new media anchor, then the sum of the weight values of these 3 same elements is used as the information similarity value of this reference new media anchor.

[0068] S4. Generate the similarity between the email product tag set of each reference new media anchor and the historical product promotion information tag set of the to-be-invited new media anchor.

[0069] Combined with Figure 2 , S4 specifically includes:

[0070] S41. Calculate the sub-similarity between each email product tag set of the reference new media host and each historical product promotion information tag set of the to-be-invited new media host to obtain the sub-similarity set of the reference new media host.

[0071] For example, compare each email product tag set of the reference new media host with each historical product promotion information tag set of the to-be-invited new media host one by one, obtain the number of identical elements, and use the ratio of the maximum number of identical elements obtained to the total number of elements in the email product tag set as a sub-similarity. In this way, calculate the sub-similarity between each email product tag set of the reference new media host and each historical product promotion information tag set of the to-be-invited new media host to obtain the sub-similarity set of the reference new media host. It can be understood that by only taking the maximum number to calculate the sub-similarity, redundancy in the sub-similarity set can be avoided, which may affect the subsequent calculation base. Only the maximum sub-similarity between the email product tag set and each product needs to be calculated.

[0072] S42. Obtain the first interval based on the maximum value of the sub-similarities in the sub-similarity sets of different reference new media hosts.

[0073] Specifically, the preset intervals are set as [100%, 90%], [90%, 80%], [80%, 70%], [70%, 60%], [60%, 50%], [50%, 40%], [40%, 30%], [30%, 20%], [20%, 10%], [10%, 0%]. In fact, the interval interval can be adjusted according to the distribution. If the maximum value of the sub-similarity is in a certain interval of the preset intervals, then take this preset interval as the first interval. For example, if the maximum value of the sub-similarity is 86%, then take [90%, 80%] as the first interval.

[0074] S43. Calculate the proportion of the number of elements in the sub-similarity set of the reference new media host that are in the first interval to the total number of elements in the sub-similarity set to obtain the proportion value of the reference new media host.

[0075] Continuing with the above example, for example, the number of elements in the sub-similarity set of a reference new media host that are in the first interval [90%, 80%] is 10, and the total number of elements in the sub-similarity set is 50. Then the proportion value of this reference new media host is 0.2. This step mainly characterizes the proportion of products with high sub-similarity among the products associated with the successful emails of the reference new media host.

[0076] S44. Calculate the average value of the elements in the sub-similarity set of the reference new media host that are in the first interval.

[0077] S45. Calculate the similarity of the reference new media host based on the proportion value and the average value.

[0078] S5. Calculate the final matching degree based on the similarity set and information similarity value of each reference new media anchor.

[0079] Specifically, take the product of the proportional value and the average value as the final matching degree, and take the product of the similarity and the information similarity value as the final matching degree.

[0080] S6. Use the invitation success email corresponding to the email product label set with the highest similarity of the reference new media anchor with the highest matching degree as the reference email.

[0081] By comprehensively considering the proportion of products with high sub-similarities among the products associated with the success emails of the reference new media anchors, the similarity between the email product label set of the reference new media anchor and the historical product information label set of the new media anchor to be invited, and the information similarity value between the reference new media anchor and the new media anchor to be invited, and emphasizing the influence of relatively niche new media anchor labels in terms of the information similarity value between the reference new media anchor and the new media anchor to be invited, it is possible to more comprehensively screen out the appropriate emails that truly match the new media anchor to be invited, improving the interest and invitation success rate of the new media anchor to be invited.

[0082] S7. Analyze the reference email to obtain the existing clause types; analyze the invitation success emails corresponding to the email product label sets with the sub-similarities of the reference new media anchor with the highest matching degree in the first interval to obtain multiple candidate clause types.

[0083] S8. Use the remaining clause types after removing the existing clause types from the multiple candidate clause types as the proposed supplementary clause types, and intercept the corresponding clause content and mark it in the reference email.

[0084] Examples of clauses include brand introduction type, gratitude type, copyright attribution type, privacy protection type, remuneration and incentive type, time arrangement type, cooperation form type, personalized address type, expression of affection type, welfare temptation type, etc. Among them, to analyze the clause types included in the email, keywords related to the email clauses can be collected and sorted, and keyword matching and other methods can be used to identify and intercept the clauses in the email sentence by sentence, or semantic recognition and other methods can be combined. By using the clauses in the regional invitation success emails as supplementary clauses and providing them to the reference email, it is convenient for subsequent personnel to adjust and supplement the content of the reference email as needed, send a more suitable and complete email to the new media anchor, and improve the invitation success rate.

[0085] This application also provides a customized cooperation invitation intelligent generation system, referring to Figure 3 , including:

[0086] An information acquisition module, configured to acquire the new media anchor profile information and historical product promotion information of the new media anchor to be invited, analyze the new media anchor profile information to obtain a new media anchor tag set, and analyze the historical product promotion information to obtain historical product promotion products and historical product promotion information tag sets for each historical product promotion product.

[0087] A proportion calculation module, configured to count the number of occurrences of each element in the new media anchor tag set in the reference new media anchor tag set in the new media anchor database, and calculate the proportion value of each element in the new media anchor tag set based on the number of occurrences of each element in the reference new media anchor tag set; the new media anchor database stores historical invited successful reference new media anchors and their corresponding reference new media anchor tag sets, as well as the invitation successful emails of the reference new media anchors and the email product tag sets corresponding to the invitation successful emails.

[0088] An information similarity value generation module, configured to use the reciprocal of the proportion value of each element as the weight value of each element, and generate the information similarity value of each reference new media anchor in the new media anchor database based on the weight value.

[0089] A similarity calculation module, configured to generate the similarity between the email product tag set of each reference new media anchor and the historical product promotion information tag set of the new media anchor to be invited.

[0090] A final matching degree calculation module, configured to calculate the final matching degree according to the similarity set of each reference new media anchor and the information similarity value.

[0091] An email selection module, configured to use the invitation successful email corresponding to the email product tag set with the highest similarity of the reference new media anchor with the highest matching degree as the reference email.

[0092] Among them, the information similarity value generation module includes:

[0093] An information similarity value calculation subunit, configured to calculate the sum of the weight values of the same elements in the reference new media anchor tag set of the reference new media anchor and the new media anchor tag set of the new media anchor to be invited as the information similarity value of the reference new media anchor.

[0094] In an embodiment, the similarity calculation module includes:

[0095] A sub-similarity calculation unit, configured to calculate the sub-similarity between each email product tag set of the reference new media anchor and each historical product promotion information tag set of the new media anchor to be invited to obtain the sub-similarity set of the reference new media anchor.

[0096] A first interval obtaining unit, configured to obtain a first interval based on the maximum value of the sub-similarity in the sub-similarity sets of different reference new media anchors.

[0097] A ratio value calculation unit is configured to calculate the ratio of the number of sub-similarities of a reference new media anchor that are concentrated in the first interval to the total number of elements in the sub-similarity set to obtain the ratio value of the reference new media anchor.

[0098] An average value calculation unit is configured to calculate the average value of the elements in the sub-similarity set of the reference new media anchor that are concentrated in the first interval.

[0099] A similarity calculation unit is configured to calculate the similarity of the reference new media anchor based on the ratio value and the average value.

[0100] For the specific limitations of the intelligent generation system for customized cooperation invitations, reference can be made to the limitations on the intelligent generation method for customized cooperation invitations in the above text, which will not be elaborated here. Each step of the above intelligent generation method for customized cooperation invitations can be implemented in whole or in part by software, hardware, and their combination.

[0101] The various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0102] These computational programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or apparatus (e.g., a magnetic disk, an optical disk, a memory, a programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0103] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0104] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0105] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this application can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved. No limitation is made herein.

[0106] The above specific embodiments do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims

1. Customized cooperation invitation intelligent generation method, characterized by: include: Obtain new media anchor profile information and historical product information of the new media anchor to be invited, analyze the new media anchor profile information to obtain a new media anchor tag set, analyze the historical product information to obtain historical products and historical product information tag sets of each historical product; The number of occurrences of each element in the new media anchor tag set in the reference new media anchor tag set is counted in the new media anchor database, and the proportion of each element in the new media anchor tag set is calculated based on the number of occurrences of each element in the new media anchor tag set in the reference new media anchor tag set; The new media anchor database stores historically successfully invited reference new media anchors and corresponding reference new media anchor tag sets, as well as successful invitation emails of the reference new media anchors and email product tag sets corresponding to the successful invitation emails; The inverse of the proportion of each element is used as the weight value of each element, and based on the weight value, the information similarity value of each reference new media anchor in the new media anchor database is generated; Generate the similarity between the email product label set of each reference new media anchor and the historical product information label set of the new media anchor to be invited; Calculate the final matching degree according to the similarity and information similarity value of each reference new media anchor; The successful invitation email corresponding to the email product label set with the highest similarity to the reference new media anchor with the highest matching degree is used as the reference email.

2. The customized cooperation invitation intelligent generation method according to claim 1, characterized in that: Generating information similarity values ​​of each reference new media anchor in the new media anchor database based on the weight value includes: The sum of the weight values ​​of the same elements in the reference new media anchor tag set of the reference new media anchor and the new media anchor tag set of the new media anchor to be invited is calculated as the information similarity value of the reference new media anchor.

3. The customized cooperation invitation intelligent generation method according to claim 1, characterized in that: Generate the similarity between the email product label set of each reference new media anchor and the historical product information label set of the new media anchor to be invited, including: The sub-similarity of each email product label set of the reference new media anchor and each historical product information label set of the new media anchor to be invited is calculated to obtain the sub-similarity set of the reference new media anchor.

4. The customized cooperation invitation intelligent generation method according to claim 3, characterized in that: Generating the similarity between the email product label set of each reference new media anchor and the historical product information label set of the new media anchor to be invited, further comprising: A first interval is obtained based on the maximum value of the sub-similarity in the sub-similarity sets of different reference new media anchors; Calculate the ratio of the number of reference new media anchors in the first interval in the sub-similarity set to the total number of elements in the sub-similarity set to obtain a ratio value of the reference new media anchor; Calculate the average value of the elements in the first interval in the sub-similarity set of the reference new media anchor; The similarity of the reference new media anchor is calculated based on the ratio value and the average value.

5. The customized cooperation invitation intelligent generation method according to claim 1, characterized in that: The final matching degree is calculated according to the similarity and information similarity value of each reference new media anchor, including: The product of similarity and information similarity value is taken as the final matching degree.

6. A customized cooperation invitation intelligent generation system based on the customized cooperation invitation intelligent generation method according to any one of claims 1 to 5, characterized in that: include: An information acquisition module is used to obtain the new media anchor profile information and historical product information of the new media anchor to be invited, analyze the new media anchor profile information to obtain a new media anchor tag set, analyze the historical product information to obtain historical products and historical product information tag sets of each historical product; A proportion calculation module is used to count the number of occurrences of each element in the new media anchor tag set in the reference new media anchor tag set in the new media anchor database, and calculate the proportion of each element in the new media anchor tag set based on the number of occurrences of each element in the new media anchor tag set in the reference new media anchor tag set; The new media anchor database stores historically successfully invited reference new media anchors and corresponding reference new media anchor tag sets, as well as successful invitation emails of the reference new media anchors and email product tag sets corresponding to the successful invitation emails; An information similarity value generating module, used to use the inverse of the proportion of each element as the weight value of each element, and generate the information similarity value of each reference new media anchor in the new media anchor database based on the weight value; A similarity calculation module is used to generate the similarity between the email product label set of each reference new media anchor and the historical product information label set of the new media anchor to be invited; A final matching degree calculation module, used to calculate the final matching degree according to the similarity of each reference new media anchor and the information similarity value; The email selection module is used to use the successful invitation email corresponding to the email product label set with the highest similarity to the reference new media anchor with the highest matching degree as the reference email.

7. The customized cooperation invitation intelligent generation system according to claim 6, characterized in that: The information similarity value generation module includes: The information similarity value calculation subunit is used to calculate the sum of the weight values ​​of the same elements in the reference new media anchor tag set of the reference new media anchor and the new media anchor tag set of the new media anchor to be invited as the information similarity value of the reference new media anchor.

8. The customized cooperation invitation intelligent generation system according to claim 6, characterized in that: The similarity calculation module includes: The sub-similarity calculation unit is used to calculate the sub-similarity of each email product label set of the reference new media anchor and each historical product information label set of the new media anchor to be invited to obtain the sub-similarity set of the reference new media anchor.

9. The customized cooperation invitation intelligent generation system according to claim 6, characterized in that: The similarity calculation module further includes: a first interval acquisition unit, configured to obtain a first interval based on a maximum value of sub-similarity in sub-similarity sets of different reference new media anchors; A ratio value calculation unit, used to calculate the ratio of the number of the reference new media anchor in the sub-similarity set located in the first interval to the total number of elements in the sub-similarity set to obtain a ratio value of the reference new media anchor; An average value calculation unit, used to calculate the average value of the elements located in the first interval in the sub-similarity set of the reference new media anchor; The similarity calculation unit is used to calculate the similarity of the reference new media anchor based on the ratio value and the average value.

10. The customized cooperation invitation intelligent generation system according to claim 6, characterized in that: The final matching degree calculation module also includes: The sub-matching degree calculation unit is used to take the product of the similarity and the information similarity value as the final matching degree.

Images