Welcome speech content matching method and device, and electronic device

Abstract

This invention provides a method, apparatus, and electronic device for matching welcome message content. The method first determines the current customer's bank wealth level based on their WeChat source, WeChat nickname, WeChat profile picture, WeChat UnionID, and their weights. Then, it calculates a matching score between the current customer and each piece of content based on the weights of the current customer's WeChat source, bank wealth level, and addition time, as well as the weights of the WeChat source, bank wealth level, and addition time of each piece of content. Finally, it determines the target welcome message content based on the matching score. This multi-dimensional calculation method, which obtains the matching score and then determines the target welcome message content, makes the target welcome message content more suitable for the current customer. Furthermore, the weights of the various parameters involved in the calculation are dynamically adjusted, making the process more scientific.

Description

Technical Field

[0001] This invention relates to the technical field of data matching, and in particular to a method, apparatus, and electronic device for matching welcome message content. Background Technology

[0002] Currently, after a customer successfully adds a bank employee as a WeChat friend, the first message sent to the customer is a welcome message. This welcome message can be text, H5 link, image, video, file, etc. This content needs to fully meet the customer's expectations and attract the customer, laying a good foundation for future wealth management services and customer management.

[0003] The common practice for sending welcome messages to customers involves employees manually determining the customer's origin, manually determining the content, manually copying, and manually sending. This approach is inefficient, and manually determining the appropriate content often results in inaccurate information that doesn't meet customer expectations. A better approach involves pre-setting fixed content and then applying simple matching rules to customers, such as matching their occupation. Based on the matched customer's occupation, bank employees manually send the corresponding welcome message. While this improves efficiency and relevance to the customer, the matching rules are too simplistic, leading to lower relevance between the welcome message and the customer. Pre-setting fixed content is costly to maintain, and the matching rules cannot be dynamically adjusted in a timely manner.

[0004] In summary, existing methods for matching welcome messages result in low relevance between the content and the customer, and the matching rules cannot be dynamically adjusted during the process. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a method, apparatus and electronic device for matching welcome message content, so as to alleviate the technical problem that the existing welcome message content matching methods have low adaptability to customers, and the matching rules cannot be dynamically adjusted when matching welcome message content.

[0006] In a first aspect, embodiments of the present invention provide a method for matching welcome message content, including:

[0007] The system obtains the current customer's WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID by having the customer add the employee as a WeChat friend. Based on the historical WeChat source weight, historical WeChat nickname weight, historical WeChat profile picture weight, and historical WeChat UnionID weight after the last adjustment, the system determines the weight of the WeChat source, the weight of the WeChat nickname, the weight of the WeChat profile picture, and the weight of the WeChat UnionID, respectively.

[0008] Based on the weights of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID, a WeChat item to be matched is determined from the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID. The WeChat item to be matched is then matched with the customer information pre-registered by the customer. Target customer information matching the WeChat item to be matched is obtained from the customer information pre-registered by the customer. The target customer information includes at least: the current customer's identification information and the current customer's bank wealth level.

[0009] The weights of the current customer's WeChat source, bank wealth level, and addition time are determined based on the customer's historical WeChat source weight, historical bank wealth level weight, and historical addition time weight after the last adjustment. The weights of each content's WeChat source, bank wealth level, and addition time are determined based on the historical WeChat source weight, historical bank wealth level weight, and historical addition time weight after the last adjustment.

[0010] The matching score between the current customer and each piece of content is calculated based on the weights of the current customer's WeChat source, the current customer's bank wealth level, the current customer's addition time, the WeChat source of each piece of content, the bank wealth level of each piece of content, and the addition time of each piece of content.

[0011] Based on the matching score, a target welcome message is determined from the content, and the target welcome message is sent to the current customer.

[0012] In this embodiment of the invention, a method for matching welcome message content is provided, comprising: obtaining the current customer's WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID by having the customer add the employee's WeChat account as a friend; determining the weight of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID based on the historical weights of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID after the last adjustment; determining the WeChat item to be matched from the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID based on the weights of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID; matching the WeChat item to be matched with the customer's pre-registered customer information; obtaining the target customer information matching the WeChat item to be matched from the customer's pre-registered customer information, wherein the target customer information includes at least: the current customer's identification information and the current customer's identification information. Bank wealth rating; based on the customer's historical WeChat source weight, historical bank wealth rating weight, and historical addition time weight after the last adjustment, determine the weight of the current customer's WeChat source, current customer's bank wealth rating, and current customer's addition time, respectively. Then, based on the historical WeChat source weight, historical bank wealth rating weight, and historical addition time weight of each piece of content after the last adjustment, determine the weight of the WeChat source, bank wealth rating, and addition time of each piece of content, respectively. Calculate the matching score between the current customer and each piece of content based on the current customer's WeChat source weight, current customer's bank wealth rating weight, current customer's addition time weight, and the weight of each piece of content's WeChat source weight, bank wealth rating weight, and addition time weight. Based on the matching score, determine the target welcome message content within the content and send the target welcome message to the current customer.As described above, the welcome message matching method of the present invention first determines the current customer's bank wealth level based on the current customer's WeChat source, WeChat nickname, WeChat profile picture, WeChat UnionID, and their weights. Then, it calculates the matching score between the current customer and each content based on the weights of the current customer's WeChat source, the current customer's bank wealth level, the current customer's addition time, and the weights of the WeChat source, the bank wealth level, and the addition time of each content. Finally, it determines the target welcome message content that is suitable for the current customer based on the matching score. The above method of obtaining the matching score through multi-dimensional calculation and then determining the target welcome message content makes the final target welcome message content more suitable for the current customer. Moreover, the weights of the various dimension parameters involved in the calculation are dynamically adjusted, that is, the matching process is continuously optimized and updated. In other words, with the use of this method, the determined target welcome message content is more accurate and suitable for the customer, alleviating the technical problem that the existing welcome message matching methods have low compatibility between the determined welcome message content and the customer, and that the matching rules cannot be dynamically adjusted when matching welcome message content. Attached Figure Description

[0013] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0014] Figure 1 A flowchart illustrating a method for matching welcome message content according to an embodiment of the present invention;

[0015] Figure 2 A flowchart illustrating the method for adjusting the weight of WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID as provided in this embodiment of the invention.

[0016] Figure 3 A flowchart illustrating the method for adjusting the weight of WeChat source of each content, the weight of historical bank wealth level of each content, and the weight of historical addition time of each content, provided for embodiments of the present invention.

[0017] Figure 4 A schematic diagram of a welcome message matching device provided in an embodiment of the present invention;

[0018] Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Existing methods for matching welcome messages result in low relevance between the content and the customer, and the matching rules cannot be dynamically adjusted during the process.

[0021] Based on this, the welcome message content matching method of the present invention first determines the current customer's bank wealth level based on the current customer's WeChat source, WeChat nickname, WeChat profile picture, WeChat UnionID and their weights. Then, it calculates the matching score between the current customer and each content based on the weights of the current customer's WeChat source, the current customer's historical bank wealth level, the current customer's historical addition time, and the weights of the WeChat source, the historical bank wealth level, and the historical addition time of each content. Finally, it determines the target welcome message content that is suitable for the current customer based on the matching score. The above method of obtaining the matching score through multi-dimensional calculation and then determining the target welcome message content can make the final target welcome message content more suitable for the current customer. Moreover, the weights of the various dimension parameters involved in the calculation are dynamically adjusted, that is, the matching process is continuously optimized and updated. In other words, as this method is used, the determined target welcome message content is more accurate and suitable for the customer.

[0022] To facilitate understanding of this embodiment, a method for matching welcome message content disclosed in this embodiment of the invention will first be described in detail.

[0023] Example 1:

[0024] According to an embodiment of the present invention, an embodiment of a method for matching welcome message content is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0025] Figure 1 This is a flowchart of a method for matching welcome message content according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0026] Step S102: Obtain the current customer's WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID by having the customer add the employee's WeChat account as a friend. Then, determine the weight of WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID based on the historical weight of WeChat source, historical weight of WeChat nickname, historical weight of WeChat avatar, and historical weight of WeChat UnionID after the last adjustment.

[0027] In this embodiment of the invention, the above-mentioned welcome message content matching method can be applied to the welcome message content matching system. The current customer's WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID are obtained by the customer adding the employee's WeChat Work friend. Specifically, when the bank's employee uses their WeChat Work and the customer successfully adds the customer as a friend by scanning the WeChat Work QR code with their personal WeChat, the current customer's WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID can be obtained.

[0028] The aforementioned WeChat source is the source marked on the QR code of the bank employee's corporate WeChat account, meaning that the QR code contains source information. For example, a bank's account manager helps a company's employees apply for salary cards. During the application process, the account manager has all the employees add the bank's WeChat official account. When adding the accounts, the account manager marks the source tag on the WeChat official account's QR code as "payment on behalf." Therefore, when the company's employees scan the QR code to add the account as a friend, their WeChat source will be "payment on behalf." Another example is a bank partnering with a merchant. The account manager has the merchant add the bank's WeChat official account. During this process, the account manager marks the source tag on the QR code as the specific activity name. Therefore, when the merchant scans the QR code to add the account as a friend, their WeChat source will be the specific activity name. Yet another example is when an account manager opens a bank account for a customer. The account manager has the customer add the bank's WeChat official account. During this process, the account manager marks the source tag on the QR code as the customer's identification number (e.g., their ID card number). Therefore, when the customer scans the QR code to add the account as a friend, their WeChat source will be their identification number.

[0029] After obtaining the current customer's WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID, the weights of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID can be determined based on the historical weights of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID, respectively, according to the previously adjusted historical weights. For example, if the current customer's WeChat source is a proxy, the historical weights of proxy in the previously adjusted historical WeChat source weights were 6, the historical weight of WeChat UnionID was 10, the historical weight of WeChat nickname was 1, and the historical weight of WeChat profile picture was... If the weight of the WeChat source is 1, then the weight of the WeChat nickname, the weight of the WeChat profile picture, and the weight of the WeChat UnionID are determined to be 6, 1, and 10 respectively. For example, if the current customer's WeChat source is their ID number, and the historical WeChat source weights after the last adjustment have the following weights: ID number 10, WeChat UnionID 6, WeChat nickname 1, and WeChat profile picture 1, then the weight of the current customer's WeChat source is determined to be 10, WeChat nickname 1, WeChat profile picture 1, and WeChat UnionID 6 respectively.

[0030] It should be noted that if the historical WeChat source weight, historical WeChat nickname weight, historical WeChat avatar weight, and historical WeChat UnionID weight are not available, then when matching the welcome message content for the first time, the historical WeChat source weight, historical WeChat nickname weight, historical WeChat avatar weight, and historical WeChat UnionID weight can be pre-set weight values ​​for each experience, or they can be initial weight values ​​obtained after testing and matching based on some basic data.

[0031] Step S104: Based on the weight of WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID, determine the WeChat item to be matched from WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID, and match the WeChat item to be matched with the customer information reserved by the customer. Obtain the target customer information that matches the WeChat item to be matched from the customer information reserved by the customer. The target customer information includes at least: the current customer's identification information and the current customer's bank wealth level.

[0032] Specifically, among the weights of WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID, the highest weight is determined, and the item corresponding to the highest weight is taken as the WeChat item to be matched. For example, if the weight of WeChat source is the highest, then WeChat source is taken as the WeChat item to be matched, and the WeChat source is matched with the customer's pre-registered customer information. Then, the target customer information that matches the above-mentioned WeChat source is obtained from the customer's pre-registered customer information, namely the current customer's identification information and the current customer's bank wealth level, etc.

[0033] The customer information reserved by the aforementioned customer refers to customer-related information reserved by the customer with the bank, such as personal information reserved by the customer when conducting business at the bank. The main purpose of this process is to determine the wealth level (also known as asset information) of the friend (i.e., the customer) added by the bank employee. After the bank employee adds the customer as a WeChat friend, it can only be confirmed that the customer is a friend, but the customer's specific identification information and bank wealth level have not yet been determined. Therefore, it is necessary to determine the friend's identification information and bank wealth level according to the above matching process. If the WeChat source is used as the WeChat item to be matched with the customer's reserved customer information, the WeChat source may be the customer's identification number. Then, by matching the identification number with the customer's reserved customer information, the identification number of the customer information can be matched as the target customer information of the aforementioned identification number, and the target customer information such as the customer's name, age, and bank wealth level corresponding to the identification number can be obtained.

[0034] The customer information reserved by the above customers is the complete set of customer information stored in the system.

[0035] Step S106: Based on the customer's historical WeChat source weight, the customer's historical bank wealth level weight, and the customer's historical addition time weight after the last adjustment, determine the weight of the current customer's WeChat source, the weight of the current customer's bank wealth level, and the weight of the current customer's addition time, respectively. Based on the historical WeChat source weight, the historical bank wealth level weight, and the historical addition time weight of each content after the last adjustment, determine the weight of the WeChat source, the weight of the bank wealth level, and the weight of the addition time of each content, respectively.

[0036] After obtaining the current customer's bank wealth level, the weights of the current customer's WeChat source, bank wealth level, and addition time are determined based on the customer's historical WeChat source weights after the last adjustment, the customer's historical bank wealth level weights, and the customer's historical addition time weights. For example, in the customer's historical WeChat source weights after the last adjustment, the weight of the customer who was a pay-on-delivery customer was 7, the weight of the customer's highest wealth level was 10, and the weight of the customer who was added yesterday was 3. Since the current customer's WeChat source is pay-on-delivery, the weight of the current customer's WeChat source is 7. Since the current customer's bank wealth level is the highest wealth level, the weight of the current customer's bank wealth level is 10. Since the current customer's addition time (i.e., the time when the friend was added) was yesterday, the weight of the current customer's addition time is 3.

[0037] The weights of each content's WeChat source, bank wealth level, and addition time are determined based on the historical WeChat source weight, historical bank wealth level weight, and historical addition time weight, respectively, after the last adjustment. Specifically, the historical WeChat source weight of each content after the last adjustment can be used as the weight of the WeChat source of each content, the historical bank wealth level weight of each content after the last adjustment can be used as the weight of the bank wealth level of each content, and the historical addition time weight of each content after the last adjustment can be used as the weight of the addition time of each content.

[0038] It should be noted that if the customer's historical WeChat source weight, historical bank wealth level weight, and historical addition time weight after the last adjustment are not available, then when matching the welcome message content for the first time, the customer's historical WeChat source weight, historical bank wealth level weight, and historical addition time weight after the last adjustment can be a pre-set weight value for each experience, or it can be an initial weight value obtained after testing and matching some basic data. Similarly, the historical WeChat source weight, historical bank wealth level weight, and historical addition time weight of each content after the last adjustment can also be designed and implemented in this way. The WeChat source weight in this step is different from the WeChat source weight in step S102 above, because the two have different functions. The WeChat source weight in step S102 is to determine the current customer's bank wealth level, while the WeChat source weight here is to match appropriate welcome message content.

[0039] In addition, the system contains a structured content pool, which contains a large number of welcome messages (i.e., content). Each welcome message has a corresponding tag of the above three dimensions and its corresponding weight. For example, a welcome message with a WeChat source of "posted on behalf of someone else" has a weight of 3, a WeChat source of "customer's ID number" has a weight of 10, and a WeChat source of "specific event name" has a weight of 6.

[0040] Step S108: Calculate the matching score between the current customer and each piece of content based on the weight of the current customer's WeChat source, the weight of the current customer's bank wealth level, the weight of the current customer's addition time, the weight of the WeChat source of each piece of content, the weight of the bank wealth level of each piece of content, and the weight of the addition time of each piece of content.

[0041] Specifically, the weighted average of each dimension of each content and the corresponding weights of each dimension of the current customer can be calculated to obtain the matching score between the current customer and each content.

[0042] Step S110: Determine the target welcome message content in the content based on the matching score, and send the target welcome message content to the current customer.

[0043] Specifically, the aforementioned target welcome message can be one or two, and the target welcome message can be sent by the system to the current customer's WeChat account via Enterprise WeChat.

[0044] In this embodiment of the invention, a method for matching welcome message content is provided, comprising: obtaining the current customer's WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID by having the customer add the employee's WeChat account as a friend; determining the weight of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID based on the historical weights of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID, respectively, after the last adjustment; determining the WeChat item to be matched from the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID based on the weights of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID; matching the WeChat item to be matched with the customer's pre-registered customer information; obtaining the target customer information matching the WeChat item to be matched from the customer's pre-registered customer information, wherein the target customer information includes at least: the current customer's identification information and the current customer's bank wealth level; and so on. Based on the customer's historical WeChat source weight, historical bank wealth level weight, and historical addition time weight after the last adjustment, the weights of the current customer's WeChat source, historical bank wealth level, and historical addition time are determined. Then, based on the historical WeChat source weight, historical bank wealth level weight, and historical addition time weight of each content item after the last adjustment, the weights of the current customer's WeChat source, historical bank wealth level, and historical addition time are determined. A matching score is calculated between the current customer and each content item based on these weights. The target welcome message is then determined within the content based on the matching score and sent to the current customer.As described above, the welcome message matching method of the present invention first determines the current customer's bank wealth level based on the current customer's WeChat source, WeChat nickname, WeChat profile picture, WeChat UnionID, and their weights. Then, it calculates the matching score between the current customer and each content based on the weights of the current customer's WeChat source, the current customer's bank wealth level, the current customer's addition time, and the weights of the WeChat source, the bank wealth level, and the addition time of each content. Finally, it determines the target welcome message content that is suitable for the current customer based on the matching score. The above method of obtaining the matching score through multi-dimensional calculation and then determining the target welcome message content makes the final target welcome message content more suitable for the current customer. Moreover, the weights of the various dimension parameters involved in the calculation are dynamically adjusted, that is, the matching process is continuously optimized and updated. In other words, with the use of this method, the determined target welcome message content is more accurate and suitable for the customer, alleviating the technical problem that the existing welcome message matching methods have low compatibility between the determined welcome message content and the customer, and that the matching rules cannot be dynamically adjusted when matching welcome message content.

[0045] The above provides a brief overview of the method for matching welcome messages according to the present invention. The specific details involved will be described in detail below.

[0046] In an alternative embodiment of the present invention, reference is made to... Figure 2 The method also includes:

[0047] Step S201: Obtain the standard customer information reported after the current customer browses the target welcome message content;

[0048] Specifically, if the target welcome message is about a bank's wealth management product, and the current customer browses and purchases the product, then the system can obtain the customer's real information (such as ID number) at the time of purchase, which is standard customer information. For another example, if the current customer needs to authorize their mobile phone number before browsing the target welcome message, then the system can obtain the real customer's mobile phone number, which is standard customer information.

[0049] Step S202: Determine the accuracy of the target customer information based on the standard customer information;

[0050] Specifically, the standard customer information is compared with the target customer information determined earlier. If they are the same, the target customer information is accurate; if they are different, the target customer information is inaccurate.

[0051] Step S203: Adjust the weights of WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID according to the accuracy of the target customer information to obtain the adjusted weights of WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID.

[0052] Specifically, if the current customer's WeChat source is a third-party sender, among the original weights of WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID, the weight of WeChat source is the highest. Later, based on the standard customer information reported by the current customer, the target customer information is determined to be inaccurate. In this case, the weight of WeChat source needs to be reduced, and the weight of WeChat UnionID needs to be increased (generally, the weights of WeChat source and WeChat UnionID are more important, while the weights of WeChat nickname and WeChat profile picture are very small).

[0053] For example, if a large number of customers are using WeChat accounts that are being sent through third-party services, and the above information reveals that the identified target customer information is inaccurate (i.e., the success rate is very low), then we can analyze the WeChat items that were used to identify the target customer information and find that they are not reasonable. In this case, we can reduce the weight of the WeChat items to be matched and increase the weight of other WeChat items (i.e., the weight of relevant items in WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID), so that the target customer information identified in subsequent matching will be more accurate.

[0054] Step S204: The adjusted weights of the WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID are used as the historical WeChat source weights, historical WeChat nickname weights, historical WeChat avatar weights, and historical WeChat UnionID weights for matching the next welcome message content.

[0055] In an optional embodiment of the present invention, when the number of target welcome messages is one, refer to Figure 3 The method also includes:

[0056] Step S301: Obtain the browsing time of the current customer's browsing of the target welcome message content and the number of chat inquiries made by the current customer regarding the target welcome message content;

[0057] Step S302: Determine the accuracy of the target welcome message content based on browsing time and number of chat inquiries;

[0058] Specifically, browsing time and chat consultation frequency can be segmented, with a certain score assigned to each segment. For example, browsing time of 1-10 seconds is worth 10 points, browsing time of 10 seconds to 1 minute is worth 30 points, browsing time of 1 minute to 2 minutes is worth 50 points, chat consultation frequency of 0 is worth 10 points, and chat consultation frequency of 1-2 is worth 60 points. The current customer's browsing time and chat consultation frequency are then matched with the above segments. Based on the matching results, the scores for the current customer's browsing time and chat consultation frequency are determined. The two are then weighted and calculated (the weight of browsing time can be preset to 0.4, and the weight of chat consultation frequency to 0.6) to obtain the final score. If the final score is greater than the preset threshold, it means that the target welcome message content is accurate. If the final score is not greater than the preset threshold, it means that the target welcome message content is inaccurate. Alternatively, the weights can be adjusted based on the final score.

[0059] Of course, you can also simply determine the accuracy of the target welcome message content based on whether the browsing time exceeds the preset time and whether the number of chat inquiries exceeds the preset number.

[0060] Step S303: Based on the accuracy of the target welcome message content, adjust the weight of the WeChat source of each content, the weight of the historical bank wealth level of each content, and the weight of the historical addition time of each content to obtain the adjusted weight of the WeChat source of each content, the adjusted weight of the historical bank wealth level of each content, and the adjusted weight of the historical addition time of each content.

[0061] Specifically, if the accuracy of the target welcome message is determined to be very high (e.g., the score is very high), it indicates that the weights of the WeChat source of the content, the historical bank wealth level of the content, and the historical addition time of the content are relatively reasonable. In this case, the weights of the larger of the three factors should be increased, and the weights of the smaller factors should be decreased. If the accuracy of the target welcome message is determined to be very low, it indicates that the weights of the WeChat source of the content, the historical bank wealth level of the content, and the historical addition time of the content are unreasonable. In this case, the weights of the larger factors should be decreased, and the weights of the smaller factors should be increased.

[0062] For example, if there are a large number of customers and the above process reveals that the target welcome messages are inaccurate (i.e., the accuracy rate is very low), then we can analyze which of the following factors is unreasonable: the weight of the WeChat source of the target welcome message, the weight of the historical bank wealth level of the content, and the weight of the historical addition time of the content. We can then adjust these factors to make the subsequent target welcome messages more accurate.

[0063] Step S304: The adjusted weights of the WeChat source of each content, the historical bank wealth level of each content, and the historical addition time of each content are respectively used as the historical WeChat source weight, historical bank wealth level weight, and historical addition time weight of each content for matching the next welcome message content.

[0064] In an optional embodiment of the present invention, when the number of target welcome messages is two, the method further includes:

[0065] (1) Obtain the first browsing time of the current customer's first target welcome message content and the first number of chat inquiries made by the current customer regarding the first target welcome message content; and obtain the second browsing time of the current customer's second target welcome message content and the second number of chat inquiries made by the current customer regarding the second target welcome message content.

[0066] (2) Determine the standard target welcome message content based on the first browsing time, the first number of chat inquiries, the second browsing time, and the second number of chat inquiries, in the first target welcome message content and the second target welcome message content;

[0067] Specifically, browsing time and the number of chat inquiries can be segmented, with a certain score assigned to each segment. For example, browsing time of 1-10 seconds is worth 10 points, browsing time of 10 seconds to 1 minute is worth 30 points, browsing time of 1 minute to 2 minutes is worth 50 points, 0 chat inquiries is worth 10 points, and 1-2 chat inquiries are worth 60 points. Then, the current customer's first browsing time, first chat inquiries, second browsing time, and second chat inquiries are matched with the above segments. Based on the matching results, the score for the current customer's first browsing time and first chat inquiries regarding the first target welcome message content is determined, and then the score for the second... The system performs a weighted calculation (the weight of browsing time can be preset to 0.4, and the weight of chat consultation count to 0.6) to obtain the first score of the current customer for the first target welcome message content. Based on the matching results, the system determines the second score of the current customer for the second target welcome message content based on the browsing time and the second score of chat consultation count. The two scores are then weighted again (the weight of browsing time can be preset to 0.4, and the weight of chat consultation count to 0.6) to obtain the second score of the current customer for the second target welcome message content. Based on the size of the first score and the second score, a standard target welcome message content is determined between the first target welcome message content and the second target welcome message content.

[0068] (3) Based on the standard target welcome message content, the weights of the WeChat source of each content, the weights of the historical bank wealth level of each content, the weights of the historical addition time of each content, the weights of the current customer's WeChat source, the weights of the current customer's historical bank wealth level, and the weights of the current customer's historical addition time are adjusted to obtain the adjusted weights of the WeChat source of each content, the adjusted weights of the historical bank wealth level of each content, the adjusted weights of the historical addition time of each content, the adjusted weights of the current customer's WeChat source, the adjusted weights of the current customer's historical bank wealth level, and the adjusted weights of the current customer's historical addition time.

[0069] Specifically, if the accuracy of the standard target welcome message is determined to be very high (e.g., the score is very high), further analysis based on the first and second target welcome message content reveals which of the following is most reasonable: the weight of the content's WeChat source, the weight of the content's historical bank wealth level, the weight of the content's historical addition time, the weight of the current customer's WeChat source, the weight of the current customer's historical bank wealth level, and the weight of the current customer's historical addition time. In this case, the weight of the more important dimension will be increased, and the weight of the less important dimension will be decreased. Conversely, if the accuracy of the standard target welcome message is determined to be very low, further analysis based on the first and second target welcome message content reveals which of the following is most unreasonable: the weight of the content's WeChat source, the weight of the content's historical bank wealth level, the weight of the content's historical addition time, the weight of the current customer's WeChat source, the weight of the current customer's historical bank wealth level, and the weight of the current customer's historical addition time. In this case, the weight of the less important dimension will be increased, and the weight of the more important dimension will be decreased.

[0070] Furthermore, based on the accuracy of a large number of customers, a comprehensive analysis can be conducted on the three dimensions of the aforementioned customers and the three dimensions of the content, and then the weights of the relevant dimensions can be adjusted.

[0071] (4) The adjusted weights of the WeChat source of each content, the adjusted weights of the historical bank wealth level of each content, and the adjusted weights of the historical addition time of each content are respectively used as the historical WeChat source weights, historical bank wealth level weights, and historical addition time weights of each content for matching the next welcome message content. The adjusted weights of the current customer's WeChat source, the adjusted weights of the current customer's historical bank wealth level, and the adjusted weights of the current customer's historical addition time are respectively used as the customer's historical WeChat source weights, historical bank wealth level weights, and historical addition time weights for matching the next welcome message content.

[0072] In an optional embodiment of the present invention, the matching score between the current customer and each piece of content is calculated based on the weights of the current customer's WeChat source, the current customer's historical bank wealth level, the current customer's historical addition time, the WeChat source of each piece of content, the historical bank wealth level of each piece of content, and the historical addition time of each piece of content. Specifically, this includes:

[0073] The matching score between the current customer and each piece of content is calculated by weighting the current customer's WeChat source, historical bank wealth level, and historical addition time with the weights of each piece of content's WeChat source, historical bank wealth level, and historical addition time.

[0074] In an optional embodiment of the present invention, determining the target welcome message content based on the matching score specifically includes:

[0075] (1) Determine the target match score from the match scores;

[0076] Specifically, the target match score is the highest match score and / or the second highest match score among the match scores.

[0077] If the highest and second highest matching scores are close (the difference between them is a threshold; if the difference is less than this threshold, they are considered close), the system will automatically adjust based on the accuracy of the target welcome message. In this case, the target matching score will be the highest and second highest matching scores. If the highest and second highest matching scores are not close, the target matching score will be the highest matching score.

[0078] (2) Use the content corresponding to the target matching score as the target welcome message content.

[0079] Through practice, it has been found that the welcome message content matching method of this invention can automatically send welcome message content, which can improve customer readability; if the content is a recommendation of financial products, it can further improve the order conversion rate of financial products. At the same time, based on customer behavior and feedback after sending welcome message content, the weight of each dimension of matching is further optimized, which is more scientific and solves business problems.

[0080] Example 2:

[0081] This invention also provides a welcome message content matching device, which is mainly used to execute the welcome message content matching method provided in Embodiment 1 of this invention. The welcome message content matching device provided in this invention will be described in detail below.

[0082] Figure 4This is a schematic diagram of a welcome message matching device according to an embodiment of the present invention, such as... Figure 4 As shown, the device mainly includes: an acquisition unit 10, a determination and matching unit 20, a determination unit 30, a calculation unit 40, and a determination and sending unit 50, wherein:

[0083] The acquisition unit is used to obtain the current customer's WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID by having the customer add the employee's WeChat WeChat friend. Based on the historical WeChat source weight, historical WeChat nickname weight, historical WeChat profile picture weight, and historical WeChat UnionID weight after the last adjustment, the weight of WeChat source, the weight of WeChat nickname, the weight of WeChat profile picture, and the weight of WeChat UnionID are determined respectively.

[0084] The determination and matching unit is used to determine the WeChat item to be matched from the WeChat source, WeChat nickname, WeChat avatar and WeChat UnionID according to the weight of WeChat source, WeChat nickname, WeChat avatar and WeChat UnionID, and match the WeChat item to be matched with the customer information reserved by the customer. The target customer information that matches the WeChat item to be matched is obtained from the customer information reserved by the customer. The target customer information includes at least: the current customer's identification information and the current customer's bank wealth level.

[0085] The determination unit is used to determine the weight of the current customer's WeChat source, the weight of the current customer's bank wealth level, and the weight of the current customer's addition time based on the customer's historical WeChat source weight, the customer's historical bank wealth level weight, and the customer's historical addition time weight after the last adjustment. It also determines the weight of each content's WeChat source, the weight of each content's bank wealth level, and the weight of each content's addition time based on the historical WeChat source weight, the weight of each content's historical bank wealth level weight, and the weight of each content's historical addition time weight after the last adjustment.

[0086] The calculation unit is used to calculate the matching score between the current customer and each piece of content based on the weight of the current customer's WeChat source, the weight of the current customer's bank wealth level, the weight of the current customer's addition time, the weight of the WeChat source of each piece of content, the weight of the bank wealth level of each piece of content, and the weight of the addition time of each piece of content.

[0087] The determination and sending unit is used to determine the target welcome message content in the content based on the matching score, and send the target welcome message content to the current customer.

[0088] In this embodiment of the invention, a welcome message content matching device is provided, comprising: obtaining the current customer's WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID by having the customer add the employee's WeChat account as a friend; determining the weight of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID based on the historical weight of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID after the last adjustment; determining the WeChat item to be matched from the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID based on the weight of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID; matching the WeChat item to be matched with the customer's pre-registered customer information; obtaining the target customer information that matches the WeChat item to be matched from the customer's pre-registered customer information, wherein the target customer information includes at least: the current customer's identification information and the current customer's ID information. Bank wealth rating; based on the customer's historical WeChat source weight, historical bank wealth rating weight, and historical addition time weight after the last adjustment, determine the weight of the current customer's WeChat source, current customer's bank wealth rating, and current customer's addition time, respectively. Then, based on the historical WeChat source weight, historical bank wealth rating weight, and historical addition time weight of each piece of content after the last adjustment, determine the weight of the WeChat source, bank wealth rating, and addition time of each piece of content, respectively. Calculate the matching score between the current customer and each piece of content based on the current customer's WeChat source weight, current customer's bank wealth rating weight, current customer's addition time weight, and the weight of each piece of content's WeChat source weight, bank wealth rating weight, and addition time weight. Based on the matching score, determine the target welcome message content within the content and send the target welcome message to the current customer.As described above, the welcome message matching device of the present invention first determines the current customer's bank wealth level based on the current customer's WeChat source, WeChat nickname, WeChat profile picture, WeChat UnionID, and their weights. Then, it calculates the matching score between the current customer and each content based on the weights of the current customer's WeChat source, the current customer's bank wealth level, the current customer's addition time, and the weights of the WeChat source, the bank wealth level, and the addition time of each content. Finally, it determines the target welcome message content that is suitable for the current customer based on the matching score. The above method of obtaining the matching score through multi-dimensional calculation and then determining the target welcome message content makes the final target welcome message content more suitable for the current customer. Moreover, the weights of the various dimension parameters involved in the calculation are dynamically adjusted, that is, the matching process is continuously optimized and updated. In other words, with the use of this method, the determined target welcome message content is more accurate and suitable for the customer, alleviating the technical problem that the existing welcome message matching methods have low compatibility between the determined welcome message content and the customer, and that the matching rules cannot be dynamically adjusted when matching welcome message content.

[0089] Optionally, the device is also used to: obtain standard customer information reported by the current customer after browsing the target welcome message content; determine the accuracy of the target customer information based on the standard customer information; adjust the weights of WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID according to the accuracy of the target customer information, to obtain adjusted weights of WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID; and use the adjusted weights of WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID as historical weights of WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID for matching the next welcome message content.

[0090] Optionally, when there is only one target welcome message, the device is further configured to: obtain the browsing time of the current customer's browsing of the target welcome message and the number of chat inquiries made by the current customer regarding the target welcome message; determine the accuracy of the target welcome message based on the browsing time and the number of chat inquiries; adjust the weights of the WeChat source, the historical bank wealth level, and the historical addition time of each content according to the accuracy of the target welcome message, to obtain the adjusted weights of the WeChat source, the historical bank wealth level, and the historical addition time of each content; and use the adjusted weights of the WeChat source, the historical bank wealth level, and the historical addition time of each content as the historical WeChat source weight, the historical bank wealth level weight, and the historical addition time weight of each content for matching the next welcome message.

[0091] Optionally, when there are two target welcome messages, the device is further configured to: obtain the first browsing time of the current customer browsing the first target welcome message content and the first number of chat inquiries by the current customer regarding the first target welcome message content; and obtain the second browsing time of the current customer browsing the second target welcome message content and the second number of chat inquiries by the current customer regarding the second target welcome message content; determine standard target welcome message content from the first and second target welcome message content based on the first browsing time, the first number of chat inquiries, the second browsing time, and the second number of chat inquiries; and adjust the weights of the WeChat source of each content, the historical bank wealth level of each content, the historical addition time of each content, the current customer's WeChat source, the current customer's historical bank wealth level, and the current customer's historical addition time based on the standard target welcome message content to obtain the adjusted weights of the WeChat source of each content. The adjusted weights of the historical bank wealth rating, historical addition time, current customer's WeChat source, historical bank wealth rating, and historical addition time for each content item are used as the historical WeChat source weight, historical bank wealth rating weight, and historical addition time weight for each content item, respectively, for matching the next welcome message content. Similarly, the adjusted weights of the current customer's WeChat source, historical bank wealth rating, and historical addition time weight are used as the customer's historical WeChat source weight, historical bank wealth rating weight, and historical addition time weight for matching the next welcome message content.

[0092] Optionally, the calculation unit is also used to: perform weighted calculations on the weight of the current customer's WeChat source, the weight of the current customer's historical bank wealth level, and the weight of the current customer's historical addition time, respectively, with the weight of the WeChat source of each content, the weight of the historical bank wealth level of each content, and the weight of the historical addition time of each content, to obtain the matching score between the current customer and each content.

[0093] Optionally, the determining and sending unit is also used to: determine the target matching score in the matching score; and use the content corresponding to the target matching score as the target welcome message content.

[0094] Optionally, the target matching score is the highest matching score and / or the second highest matching score among the matching scores.

[0095] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0096] like Figure 5 As shown in the embodiment of this application, an electronic device 600 includes a processor 601, a memory 602, and a bus. The memory 602 stores machine-readable instructions executable by the processor 601. When the electronic device is running, the processor 601 communicates with the memory 602 via the bus. The processor 601 executes the machine-readable instructions to perform the steps of the above-described welcome message content matching method.

[0097] Specifically, the memory 602 and processor 601 mentioned above can be general-purpose memory and processor, without any specific limitations. When the processor 601 runs the computer program stored in the memory 602, it can execute the matching method for the welcome message content mentioned above.

[0098] The processor 601 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 601 or by instructions in software form. The processor 601 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may 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 gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 602, and processor 601 reads the information from memory 602 and, in conjunction with its hardware, completes the steps of the above method.

[0099] Corresponding to the above-described method for matching welcome messages, this application also provides a computer-readable storage medium storing machine-executable instructions. When these machine-executable instructions are invoked and executed by a processor, they cause the processor to perform the steps of the above-described method for matching welcome messages.

[0100] The welcome message matching device provided in this application embodiment can be specific hardware on the device or software or firmware installed on the device. The device provided in this application embodiment has the same implementation principle and technical effects as the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0101] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0102] For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0103] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0104] In addition, the functional units in the embodiments provided in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0105] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the vehicle marking method described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0107] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for matching welcome message content, characterized in that, include: The system obtains the current customer's WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID by having the customer add the employee as a WeChat friend. Based on the historical WeChat source weight, historical WeChat nickname weight, historical WeChat profile picture weight, and historical WeChat UnionID weight after the last adjustment, the system determines the weight of the WeChat source, the weight of the WeChat nickname, the weight of the WeChat profile picture, and the weight of the WeChat UnionID, respectively. Based on the weights of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID, a WeChat item to be matched is determined from the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID. The WeChat item to be matched is then matched with the customer information pre-registered by the customer. Target customer information matching the WeChat item to be matched is obtained from the customer information pre-registered by the customer. The target customer information includes at least: the current customer's identification information and the current customer's bank wealth level. The weights of the current customer's WeChat source, bank wealth level, and addition time are determined based on the customer's historical WeChat source weight, historical bank wealth level weight, and historical addition time weight after the last adjustment. The weights of each content's WeChat source, bank wealth level, and addition time are determined based on the historical WeChat source weight, historical bank wealth level weight, and historical addition time weight after the last adjustment. The matching score between the current customer and each piece of content is calculated based on the weights of the current customer's WeChat source, the current customer's bank wealth level, the current customer's addition time, the WeChat source of each piece of content, the bank wealth level of each piece of content, and the addition time of each piece of content. Based on the matching score, a target welcome message is determined from the content, and the target welcome message is sent to the current customer. Specifically, when matching the welcome message content for the first time, the weights of the WeChat source, the WeChat nickname, the WeChat avatar, and the WeChat UnionID are preset first initial weights. When matching the welcome message content for the first time, the customer's historical WeChat source weight, historical bank wealth level weight, and historical addition time weight are the preset second initial weights after the last adjustment. When matching the welcome message content for the first time, the historical WeChat source weight, historical bank wealth level weight, and historical addition time weight of each content after the last adjustment are the preset third initial weights. The method further includes: Obtain the standard customer information reported by the current customer after browsing the target welcome message content; The accuracy of the target customer information is determined based on the standard customer information. Based on the accuracy of the target customer information, the weights of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID are adjusted to obtain the adjusted weights of the WeChat source, WeChat nickname, WeChat profile picture, and WeChat UnionID. The adjusted weights of the WeChat source, the adjusted weights of the WeChat nickname, the adjusted weights of the WeChat avatar, and the adjusted weights of the WeChat UnionID are respectively used as the historical WeChat source weights, historical WeChat nickname weights, historical WeChat avatar weights, and historical WeChat UnionID weights for matching the content of the next welcome message. When the number of target welcome messages is one, the method further includes: Obtain the browsing time of the current customer when viewing the target welcome message content, and the number of chat inquiries made by the current customer regarding the target welcome message content; The accuracy of the target welcome message content is determined based on the browsing time and the number of chat inquiries. Based on the accuracy of the target welcome message content, the weights of the WeChat source of each content, the historical bank wealth level of each content, and the historical addition time of each content are adjusted to obtain the adjusted weights of the WeChat source of each content, the historical bank wealth level of each content, and the historical addition time of each content. The adjusted weights of the WeChat source of each content, the historical bank wealth level of each content, and the historical addition time of each content will be used as the historical WeChat source weight, historical bank wealth level weight, and historical addition time weight of each content, respectively, for matching the next welcome message content. When the number of target welcome messages is two, the method further includes: The system obtains the first browsing time of the current customer's browsing of the first target welcome message content and the first number of chat inquiries made by the current customer regarding the first target welcome message content; it also obtains the second browsing time of the current customer's browsing of the second target welcome message content and the second number of chat inquiries made by the current customer regarding the second target welcome message content. Based on the first browsing time, the first number of chat inquiries, the second browsing time, and the second number of chat inquiries, the standard target welcome message content is determined from the first target welcome message content and the second target welcome message content. Based on the standard target welcome message content, the weights of the WeChat source of each content, the historical bank wealth level of each content, the historical addition time of each content, the current customer's WeChat source, the current customer's historical bank wealth level, and the current customer's historical addition time are adjusted to obtain the adjusted weights of the WeChat source of each content, the historical bank wealth level of each content, the historical addition time of each content, the current customer's WeChat source, the current customer's historical bank wealth level, and the current customer's historical addition time. The adjusted weights of the WeChat source, the historical bank wealth level, and the historical addition time of each content are used as the historical WeChat source weight, historical bank wealth level weight, and historical addition time weight of each content, respectively, for matching the next welcome message content. The adjusted weights of the current customer's WeChat source, historical bank wealth level, and historical addition time are used as the customer's historical WeChat source weight, historical bank wealth level weight, and historical addition time weight, respectively, for matching the next welcome message content.

2. The method according to claim 1, characterized in that, The matching score between the current customer and each piece of content is calculated based on the weights of the current customer's WeChat source, the current customer's historical bank wealth level, the current customer's historical addition time, the WeChat source of each piece of content, the historical bank wealth level of each piece of content, and the historical addition time of each piece of content. This includes: The matching score between the current customer and each piece of content is calculated by weighting the weights of the current customer's WeChat source, the current customer's historical bank wealth level, and the current customer's historical addition time with the weights of the WeChat source, the historical bank wealth level, and the historical addition time of each piece of content.

3. The method according to claim 1, characterized in that, Based on the matching score, the target welcome message content is determined within the content, including: The target match score is determined from the match scores; The content corresponding to the target matching score is used as the target welcome message content.

4. The method according to claim 3, characterized in that, The target matching score is the highest matching score and / or the second highest matching score among the matching scores.

5. A device for matching welcome message content, characterized in that, include: The acquisition unit is used to obtain the current customer's WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID by having the customer add the employee's WeChat WeChat friend. Based on the historical WeChat source weight, historical WeChat nickname weight, historical WeChat avatar weight, and historical WeChat UnionID weight after the last adjustment, the weight of the WeChat source, the weight of the WeChat nickname, the weight of the WeChat avatar, and the weight of the WeChat UnionID are determined respectively. The determination and matching unit is configured to determine the WeChat item to be matched from the WeChat source, WeChat nickname, WeChat avatar and WeChat UnionID according to the weight of the WeChat source, the weight of the WeChat nickname, the weight of the WeChat avatar and the weight of the WeChat UnionID, and match the WeChat item to be matched with the customer information reserved by the customer, and obtain the target customer information that matches the WeChat item to be matched from the customer information reserved by the customer, wherein the target customer information includes at least: the current customer's identification information and the current customer's bank wealth level; The determining unit is used to determine the weight of the current customer's WeChat source, the weight of the current customer's bank wealth level, and the weight of the current customer's addition time based on the customer's historical WeChat source weight, the customer's historical bank wealth level weight, and the customer's historical addition time weight after the last adjustment. It also determines the weight of each content's WeChat source, the weight of each content's bank wealth level, and the weight of each content's addition time based on the historical WeChat source weight, the weight of each content's historical bank wealth level weight, and the weight of each content's historical addition time weight after the last adjustment. The calculation unit is used to calculate the matching score between the current customer and each of the contents based on the weight of the current customer's WeChat source, the weight of the current customer's bank wealth level, the weight of the current customer's addition time, the weight of the WeChat source of each of the contents, the weight of the bank wealth level of each of the contents, and the weight of the addition time of each of the contents. A determination and sending unit is configured to determine the target welcome message content in the content based on the matching score, and send the target welcome message content to the current customer; Specifically, when matching the welcome message content for the first time, the weights of the WeChat source, the WeChat nickname, the WeChat avatar, and the WeChat UnionID are preset initial weights. When matching the welcome message content for the first time, the customer's historical WeChat source weight, historical bank wealth level weight, and historical addition time weight are the preset second initial weights after the last adjustment. When matching the welcome message content for the first time, the historical WeChat source weight, historical bank wealth level weight, and historical addition time weight of each content after the last adjustment are the preset third initial weights. The device is further configured to: acquire standard customer information reported by the current customer after browsing the target welcome message content; determine the accuracy of the target customer information based on the standard customer information; adjust the weights of the WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID based on the accuracy of the target customer information to obtain adjusted weights of the WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID; and use the adjusted weights of the WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID as the historical weights of the WeChat source, WeChat nickname, WeChat avatar, and WeChat UnionID for matching the next welcome message content. Wherein, when the number of target welcome messages is one, the device is further configured to: obtain the browsing time of the current customer browsing the target welcome message content and the number of chat inquiries made by the current customer regarding the target welcome message content; determine the accuracy of the target welcome message content based on the browsing time and the number of chat inquiries; adjust the weight of the WeChat source of each content, the weight of the historical bank wealth level of each content, and the weight of the historical addition time of each content according to the accuracy of the target welcome message content, to obtain the adjusted weight of the WeChat source of each content, the adjusted weight of the historical bank wealth level of each content, and the adjusted weight of the historical addition time of each content; and use the adjusted weight of the WeChat source of each content, the adjusted weight of the historical bank wealth level of each content, and the adjusted weight of the historical addition time of each content as the historical WeChat source weight, the historical bank wealth level weight, and the historical addition time weight of each content for matching the next welcome message content; When the number of target welcome messages is two, the device is further configured to: obtain the first browsing time of the current customer browsing the first target welcome message content and the first number of chat inquiries made by the current customer regarding the first target welcome message content; and obtain the second browsing time of the current customer browsing the second target welcome message content and the second number of chat inquiries made by the current customer regarding the second target welcome message content; determine standard target welcome message content from the first target welcome message content and the second target welcome message content based on the first browsing time, the first number of chat inquiries, the second browsing time, and the second number of chat inquiries; and adjust the weights of the WeChat source of each content, the historical bank wealth level of each content, the historical addition time of each content, the current customer's WeChat source, the current customer's historical bank wealth level, and the current customer's historical addition time based on the standard target welcome message content, to obtain... The adjusted weights of the WeChat source, historical bank wealth level, historical addition time, current customer's WeChat source, historical bank wealth level, and historical addition time for each content are used as the historical WeChat source weight, historical bank wealth level weight, and historical addition time weight for each content, respectively, for matching the next welcome message content. Similarly, the adjusted weights of the current customer's WeChat source, historical bank wealth level, and historical addition time are used as the customer's historical WeChat source weight, historical bank wealth level weight, and historical addition time weight for matching the next welcome message content.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores machine-executable instructions that, when invoked and executed by a processor, cause the processor to perform the method according to any one of claims 1 to 4.

Images