Comprehensive evaluation method and device based on user preferences, equipment and medium

Abstract

The invention provides a comprehensive evaluation method and device based on user preferences, equipment and a medium. The method comprises the steps of obtaining an information list of a user; scoring the plurality of evaluation parts of the travel place according to the information list and the objective data of the travel place; inputting the preference information of the user into the trained user preference model, and outputting the adjusted first weight value of each evaluation part; calculating a final evaluation score of the user at least based on the adjusted first weight value of each evaluation part and the score of each evaluation part; and adjusting an output planning result of the large model based on the evaluation score. According to the invention, evaluation can be carried out according to individual demands of different users.

Description

Technical Field

[0001] The present invention relates to the technical field of travel recommendation, and in particular, to a comprehensive evaluation method, device, equipment and medium based on user preferences. Background Art

[0002] With the development of AI technology, travel recommendation assistants are becoming more and more intelligent. Their recommendation methods can analyze the individual characteristics of users and display personalized recommendation results to each user through large models. An important part of travel recommendation assistants is the evaluation module, which can score multiple aspects of travel destinations and provide the most suitable planning results for users according to the evaluation results.

[0003] Existing evaluation methods can give an overall evaluation of the locations that users are interested in from a popular perspective. This evaluation can be considered relatively objective and has certain reference value. However, these methods often have the following problems: lack of in-depth consideration of users' personalized needs and inability to be flexibly adjusted according to users' specific preferences and actual application scenarios. The evaluation results provided by many methods are too general and difficult to accurately reflect the personalized needs of different users, resulting in unsatisfactory actual application effects. Some methods have adaptability problems when dealing with complex or dynamically changing situations and cannot meet the changing needs of users. Summary of the Invention

[0004] The present invention provides a comprehensive evaluation method, device, equipment and medium based on user preferences, which solves the technical problem that the existing scoring method is not ideal and cannot evaluate according to the personalized needs of different users.

[0005] According to one aspect of the present invention, there is provided a comprehensive evaluation method based on user preferences, including:

[0006] Obtain an information list of the user, where the information list at least includes the user's basic information, the user's favorite information, and the user's planning information;

[0007] Score multiple evaluation parts of the travel destination according to the information list and the objective data of the travel destination; the multiple evaluation parts at least include location, user preference, cost performance, online evaluation, advantages, and disadvantages;

[0008] Input the user's preference information into the trained user preference model, and output the first weight value of each adjusted evaluation part;

[0009] Calculate the user's final evaluation score at least based on the first weight value of each adjusted evaluation part and the scoring score of each evaluation part;

[0010] Adjust the output planning result of the large model based on the evaluation score.

[0011] Optionally, scoring multiple evaluation parts of a travel destination based on the information list and objective data of the travel destination includes:

[0012] Dividing the information list and the objective data of the travel destination by location, user preferences, cost performance, online reviews, advantages, and disadvantages, and respectively inputting them into a location score evaluation function, a user preference evaluation function, a cost performance evaluation function, an online review evaluation function, an advantage evaluation function, and a disadvantage evaluation function to score each evaluation part.

[0013] Optionally, before inputting the user's preference information into the trained user preference model to output the adjustment coefficients of each evaluation part, it further includes:

[0014] Obtaining the preference data of different users, denoising the preference data, and converting the preference data into a vector form;

[0015] Using the converted vector data as a data set to train the constructed user preference model so that the user preference model outputs the adjustment coefficients of each evaluation part.

[0016] Optionally, calculating the user's final evaluation score based on at least the first weight values of each adjusted evaluation part and the scoring scores of each evaluation part includes:

[0017] Performing a weighted calculation on the first weight values of each evaluation part and the scoring scores of each evaluation part to obtain the scores of each evaluation part;

[0018] Adding up the scores of each evaluation part to obtain the user's final evaluation score.

[0019] Optionally, calculating the user's final evaluation score based on at least the weight values of each adjusted evaluation part and the scoring scores of each evaluation part includes:

[0020] Calculating a third weight value according to the first weight values of each adjusted evaluation part and the second weight values of each evaluation part set by the user;

[0021] Performing a weighted calculation according to the third weight value and the scoring scores of each evaluation part to obtain the scores of each evaluation part;

[0022] Adding up the scores of each evaluation part to obtain the user's final evaluation score.

[0023] Optionally, location evaluation includes transportation convenience evaluation, surrounding environment evaluation, commercial and living facilities evaluation, weather and climate evaluation, and geographical location and regional evaluation;

[0024] User preference evaluation includes user collection evaluation, historical preference evaluation, travel purpose matching, budget and price preference evaluation, geographical location preference evaluation, and entertainment preference evaluation;

[0025] Cost - performance evaluation includes price - service matching evaluation, facility - service evaluation, additional service or discount evaluation, competitor comparison, time - period and season price evaluation, and surrounding market and living - cost evaluation;

[0026] Online review evaluation includes evaluation timeliness evaluation, evaluation balance evaluation, rationality evaluation of the scoring system, negative - review evaluation, and evaluation display evaluation;

[0027] Advantage evaluation includes the evaluation of the fit between advantages and user preferences, the importance and influence of advantages, the accessibility and convenience of advantages, and the user recognition and word - of - mouth of advantages;

[0028] Disadvantage evaluation includes the evaluation of the non - compliance between disadvantages and user needs, the severity and scope of influence of disadvantages, the controllability and resolvability of disadvantages, and the universality and transparency of disadvantages.

[0029] Optionally, it further includes:

[0030] Set the fourth weight values of each evaluation part in the location evaluation, the user preference evaluation, the cost - performance evaluation, the online review evaluation, the advantage evaluation, and the disadvantage evaluation respectively.

[0031] According to another aspect of the present invention, a comprehensive evaluation device based on user preferences is provided, including:

[0032] An acquisition unit for acquiring a user information list, where the information list at least includes the user's basic information, the user's collection information, and the user's planning information;

[0033] A scoring unit for scoring multiple evaluation parts of a travel location according to the information list and the objective data of the travel location; the multiple evaluation parts at least include location, user preference, cost - performance, online review, advantage, and disadvantage;

[0034] A weight - adjustment unit for inputting the user's preference information into a trained user - preference model and outputting the adjusted first weight values of each evaluation part;

[0035] An evaluation unit for calculating the user's final evaluation score based at least on the adjusted first weight values of each evaluation part and the scoring scores of each evaluation part;

[0036] A planning unit for adjusting the output planning result of the large model based on the evaluation score.

[0037] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0038] at least one processor; and

[0039] a memory communicatively connected to the at least one processor; wherein,

[0040] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the comprehensive evaluation method based on user preferences according to any embodiment of the present invention.

[0041] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the comprehensive evaluation method based on user preferences according to any embodiment of the present invention when executed.

[0042] The technical solution of the embodiment of the present invention calculates the scores of each scoring part based on the user information list, and inputs the user's preference information into the trained user preference model to output the adjusted first weight value of each evaluation part, and then calculates the final score of the user, thereby generating a highly personalized evaluation result; in addition, when the user preference information changes, different scoring results can also be obtained according to the method of the present invention, so as to give different scoring results for different user needs, and finally the output planning result of the large model will also change.

[0043] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0045] Figure 1 is a flowchart of a comprehensive evaluation method based on user preferences according to Embodiment 1 of the present invention;

[0046] Figure 2 is a flowchart of a comprehensive evaluation method based on user preferences according to Embodiment 2 of the present invention;

[0047] Figure 3It is a flowchart of a comprehensive evaluation device based on user preferences provided in Embodiment 3 of the present invention;

[0048] Figure 4 It is a schematic structural diagram of an electronic device for implementing the comprehensive evaluation method based on user preferences in the embodiments of the present invention. Detailed implementation manners

[0049] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0050] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to 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 invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0051] In the prior art, after the user experiences scenic spots, food, etc. during the travel, the user scores the scenic spots, food, etc., so as to facilitate subsequent recommendations according to the user's needs. The platform can make recommendations according to the user's scoring preferences.

[0052] In the prior art, natural language processing (NLP) technology is usually used to perform sentiment analysis on the text content of user comments. The sentiment analysis algorithm can extract the positive and negative emotions of user comments and convert them into quantitative scores. For example, mentions of "very good" or "very bad" in the comments will respectively affect the final score.

[0053] In addition, the platform will adjust the scoring weights based on the user's historical behavior and credibility. For example, users who often provide detailed evaluations or have a high activity level on the platform are usually given higher weights, thus affecting the final score.

[0054] On the one hand, some platforms will also analyze the pictures uploaded by users, and use image recognition technology to judge factors such as cleanliness and the appearance of dishes, so as to further improve the ratings.

[0055] Some other platforms will use machine learning algorithms to adjust the ratings. For example, they will use historical data and user behavior to predict which specific users' ratings are more representative, so as to fine-tune the overall rating.

[0056] Some rating systems will also consider geographical location and time factors. For example, ratings during peak tourist seasons and holidays may be adjusted to reflect the real user experience.

[0057] Existing methods can give an overall evaluation of locations of interest to users from a popular perspective. This evaluation can be considered relatively objective and has certain reference value. Existing methods have their advantages, but they often have the following main problems. Most methods lack in-depth consideration of users' personalized needs and cannot be flexibly adjusted according to users' specific preferences and actual application scenarios. The evaluation results provided by many methods are too general and difficult to accurately reflect the personalized needs of different users, resulting in unsatisfactory actual application effects. Some methods have adaptability problems when dealing with complex or dynamically changing situations and cannot meet the changing needs of users.

[0058] Embodiment 1

[0059] Figure 1 FIG. is a flowchart of an evaluation method based on user preferences provided by Embodiment 1 of the present invention. As Figure 1 shown, the method includes:

[0060] S101. Obtain a user information list, where the information list at least includes the user's basic information, the user's favorite information, and the user's planning information.

[0061] The user information list includes the user's basic information, favorite information, and planning information. Among them, the basic information may include the user's name, email, age, gender, language, etc.; the user's favorite information includes the names, types, and project names of the user's favorite travel locations; the user's planning information may include the user's travel plan, which includes the start time, end time, travel location, projects during the travel, time for each project, and the means of transportation used.

[0062] The information list may also include the user's preference information, which may include the user's preferred travel locations, travel times, travel budgets, travel means of transportation, accommodation types, food types, travel activities, travel seasons, shopping, etc.

[0063] S102. Score multiple evaluation parts of the travel destination according to the information list and the objective data of the travel destination; the multiple evaluation parts at least include location, user preference, cost performance, online evaluation, advantages, and disadvantages.

[0064] Among them, the objective data of the travel destination includes the transportation situation of the travel destination, the surrounding environment, commercial and living facilities, weather and climate, geographical location, surrounding living costs, surrounding stores, and store conditions, etc.

[0065] In this embodiment, multiple evaluation parts of the travel destination can be scored according to the information list and the objective data of the travel destination. The specific scoring method can be to convert the information list and the objective data of the travel destination into computable data, and then substitute the converted data into the preset evaluation models respectively. Multiple evaluation models can be set in this embodiment, including a location evaluation function, a user preference evaluation function, a cost performance evaluation function, an online evaluation evaluation function, an advantages evaluation function, and a disadvantages evaluation function. Finally, the location evaluation score, user preference score, cost performance score, online evaluation score, advantages score, and disadvantages score are calculated.

[0066] S103. Input the user's preference information into the trained user preference model, and output the first weight values of each evaluation part after adjustment.

[0067] The user's preference information can include the travel destination, travel time, travel budget, travel transportation means, accommodation type, food type, travel activities, travel season, shopping, etc. that the user prefers. It can also include the proportion data set by the user for each part of location, user preference, cost performance, online evaluation, advantages, and disadvantages. Among them, the first weight value represents the proportion data of each evaluation part.

[0068] The user preference model in this application is a deep learning model. The user can input the user's preference information into the user preference model, and the proportion data of multiple evaluation parts can be output. For example, when the user prefers the cost performance part during the travel, the output proportion of the cost performance part will be higher, while the proportions of other evaluation parts will decrease accordingly. In addition, when the user's preference information is the proportion data of each part, the user preference model can also fine-tune the initial proportion data of each evaluation part, so that the adjusted proportion data of each evaluation part better meets the user's preference needs.

[0069] S104. Calculate the user's final evaluation score based on at least the first weight values of each evaluation part after adjustment and the scoring scores of each evaluation part.

[0070] In this embodiment, the first weight value of each evaluation part can be multiplied by the scoring score of each evaluation part respectively and then added together to obtain the final evaluation score. Of course, the user can also adjust the first weight value again according to his own preferences to obtain the adjusted weight value, and then multiply the adjusted weight value by the scoring score of each evaluation part respectively and add them together to obtain the final evaluation score.

[0071] S105. Adjust the output planning result of the large model based on the evaluation score.

[0072] It should be noted that in a travel assistant model that can provide intelligent services for users, the travel assistant model can adjust the parameters in the travel assistant model according to the evaluation results of users, so as to provide a planning result that meets the needs of users.

[0073] The technical solution of the embodiment of the present invention calculates the scores of each scoring part based on the user information list, and inputs the user's preference information into the trained user preference model to output the adjusted first weight value of each evaluation part, and then calculates the final score of the user, thereby generating a highly personalized evaluation result; in addition, when the user's preference information changes, different scoring results can also be obtained according to the method of the present invention, so as to give different scoring results for different user needs, and finally the output planning result of the large model will also change.

[0074] Embodiment 2

[0075] Figure 2 It is a flowchart of an evaluation method based on user preferences provided by the second embodiment of the present invention. As Figure 2 shown, the method includes:

[0076] S201. Obtain the user's information list, where the information list at least includes the user's basic information, the user's favorite information, and the user's planning information.

[0077] In this embodiment, the user's information list includes the user's basic information, favorite information, the user's preference information, and the user's planning information. Among them, the basic information may include the user's name, email, age, gender, language and other information; the user's favorite information includes the name, type, and project name of the user's favorite travel destination; the user's planning information may include the user's travel plan, including the start time, end time, travel destination, items during the travel, time for each item, the means of transportation used, etc.; the user's preference information may include the user's preferred travel destination, travel time, travel budget, travel means of transportation, accommodation type, food type, travel activities, travel season, shopping, etc.

[0078] S202. Divide the information list and the objective data of the travel location according to location, user preference, cost performance, online evaluation, advantages, and disadvantages, and input them into the location score evaluation function, user preference evaluation function, cost performance evaluation function, online evaluation evaluation function, advantage evaluation function, and disadvantage evaluation function respectively to score each evaluation part.

[0079] It should be noted that the location evaluation includes the following parts, namely traffic convenience evaluation, surrounding environment evaluation, commercial and living facilities evaluation, weather and climate evaluation, and geographical location and regional evaluation. In this embodiment, the scoring ratio of each part in the location evaluation can be preset. For example, for the traffic convenience evaluation, surrounding environment evaluation, commercial and living facilities evaluation, weather and climate evaluation, and geographical location and regional evaluation, these five parts of the evaluation, the scoring ratio of each part can be set to 20%. Then the location evaluation score is the sum of the scores of these five parts multiplied by 20% respectively, which is the final location evaluation score.

[0080] Among them, the evaluation method of the traffic convenience evaluation can be: Suppose there are x1, x2... xn transportation methods to reach this location, and the initial proportion of each transportation method in the total is the same. Then the score of a single transportation method is (total score - (time required for xn to reach this location - 15 / 60) * total score). If it is less than fifteen minutes, directly take the full score. If the user prefers a certain travel mode, such as taking the subway, the proportion of this item in the total project triples.

[0081] The evaluation method of the surrounding environment evaluation can be: Score the surrounding security situation, noise situation, greening situation, building aging situation, etc. respectively and calculate the comprehensive score to obtain the surrounding environment evaluation score.

[0082] The evaluation method of the commercial and living facilities evaluation can be: Search whether there are shopping, large commercial areas, medical facilities, entertainment facilities, scenic spots, restaurants, and hotels around the travel location respectively, and conduct a comprehensive score according to the presence or absence of the above facilities to obtain the score of the commercial and living facilities evaluation.

[0083] The evaluation method of the weather and climate evaluation can be: Calculate the daily weather score, air quality score, temperature score, humidity score, altitude score, climate score, and sunlight score respectively. Among them, the daily weather score can be calculated according to the proportion of the weather that meets the user's preference in a year. Finally, calculate the comprehensive score according to the daily weather score, air quality score, temperature score, humidity score, altitude score, climate score, and sunlight score to obtain the weather and climate evaluation score.

[0084] In one embodiment, the user preference evaluation includes user collection evaluation, historical preference evaluation, travel purpose matching, budget and price preference evaluation, geographical location preference evaluation, and entertainment preference evaluation. In this embodiment, the scoring proportion of each part in the user preference evaluation can be preset. For example, for the six parts of evaluation including user collection evaluation, historical preference evaluation, travel purpose matching, budget and price preference evaluation, geographical location preference evaluation, and entertainment preference evaluation, the scoring proportion of each part can be set to 16.7%. Then the user preference score is obtained by multiplying the scores of these six parts by 16.7% respectively and then adding them up, which is the final user preference score. It should be noted that this embodiment is only an exemplary illustration, and the actual proportion of each part can be set according to user needs.

[0085] Among them, the method of user collection evaluation can score according to whether the user collects the current location. The historical preference evaluation is to judge the degree to which the location conforms to the user's historical preferences. Suppose the number of tags of the user's historical preferences is x, and the number of tags that this location conforms to is y, then the score is y / x * 100%, which is the historical preference evaluation score. The travel purpose matching evaluation scores based on whether this location is the destination of the user's travel. The evaluation method of budget and price preference evaluation can be: Suppose the average consumption price of this location is x, and the expected expense of the user for this location is y. If x > y, the score of this item is (1 - (x - y) / x) * 100%. If x <= y, the score is 100%. The evaluation method of geographical location preference evaluation can be: Score according to whether the altitude of this location conforms to the user's preference situation. The evaluation method of entertainment preference evaluation can be: Score according to the number of entertainment items provided by this location that conform to the user's favorite entertainment items, based on the number of entertainment items that conform to the user's favorite entertainment items.

[0086] In one embodiment, the cost performance evaluation includes price and service matching degree evaluation, facility and service evaluation, additional service or discount evaluation, competitor comparison, time period and season price evaluation, and surrounding market and living cost evaluation. In this embodiment, the scoring proportion of each part in the cost performance evaluation can be preset. For example, for the six parts of evaluation including price and service matching degree evaluation, facility and service evaluation, additional service or discount evaluation, competitor comparison, time period and season price evaluation, and surrounding market and living cost evaluation, the scoring proportion of each part can be set to 16.7%. Then the cost performance score is obtained by multiplying the scores of these six parts by 16.7% respectively and then adding them up, which is the final cost performance score. It should be noted that this embodiment is only an exemplary illustration, and the actual proportion of each part can be set according to user needs.

[0087] Among them, the evaluation method for the matching degree of price and service can be: the score of the service in this area is x, with a full score of 100, the price is y, and the average price that users can accept for this item is z. Then, if z > y, the score for this item is x; when z < y < 2z, the score for this item is x / 100 * (1 - (y - z) / z); if y > 2z, the score is 0. The evaluation method for the evaluation of facilities and services can be: whether all basic facilities are available, and if one is missing, 50% of the score is deducted; whether the maintenance of all facilities is good, and if there is aging, 50% is deducted; whether the service attitude is good, and the score is 0 - 100% according to the proportion; whether the efficiency is high, and the score is 0 - 100 according to the proportion. Then, the final evaluation score of facilities and services is obtained through comprehensive calculation based on the above items. The evaluation method for the evaluation of additional services or discounts can be: according to whether there are discounts and promotions for this item, whether there are free additional services, whether there is a VIP or points mechanism, and the preferential intensity of the mechanism is evaluated and comprehensively scored with the coupon item for the time being to obtain the score of the evaluation of additional services or discounts. The evaluation method for the evaluation of competitor comparison can be: the score obtained by comparing with locations of the same type: let the average price of this location be x, the average price of the same type be y, and assume the total number is m, the score is ∑m(1 - (x - y) / x) * 100 / m; the score obtained by comparing with the industry standard price; let the average price of this location be x, and the industry standard average price be y, the score is (1 - (x - y) / x) * 100, if x < y, the score is 100. Then, the evaluation score of competitor comparison is obtained through comprehensive calculation based on the scoring results of the two. The evaluation method for the evaluation of time period and season price can be: calculate the evaluation score of time period and season price according to the peak season price, off-season price and average price of this location. The evaluation method for the evaluation of the surrounding market and living cost can be: calculate the score as (1 - (x - y) / x) * 100 according to the regional price y and the price x that users can accept; calculate the score as (1 - (x - y) / x) * 100 according to the local consumption level y and the long-term residence x of users; then, the score of the surrounding market and living cost is obtained through comprehensive calculation based on the two scores.

[0088] In one embodiment, the online evaluation assessment includes the evaluation of the timeliness of evaluations, the evaluation of the balance of evaluations, the evaluation of the rationality of the scoring system, the evaluation of negative evaluations, and the evaluation of the display of evaluations. In this embodiment, the scoring ratio of each part in the online evaluation assessment can be preset. For example, for the evaluation of the timeliness of evaluations, the evaluation of the balance of evaluations, the evaluation of the rationality of the scoring system, the evaluation of negative evaluations, and the evaluation of the display of evaluations, for these five parts of the evaluation, the scoring ratio of each part can be set to 20%. Then, the score of the online evaluation assessment is the sum of the scores of these five parts multiplied by 20% respectively, which is the final score of the online evaluation assessment.

[0089] Among them, the evaluation method for the timeliness evaluation of evaluations can be: calculate the number of days difference between the most recent evaluation time and the current time as x, and the number of the most recent evaluations as y (within 7 days). The score is (7 - x) / 7 * 50 + (y - 100) / y * 50. If x > 7, the first half score is 0. If y > 200, the full score is obtained. If y < 100, the score is 0. The evaluation method for the balance evaluation of evaluations can be: evaluate according to the deep learning model, and score the objectivity and subjectivity of this evaluation. The deep learning model will score based on whether there is a behavior of merchants deliberately brushing good reviews in the evaluation, whether the evaluation contains the subjective experience of users, whether the user group is diverse, whether anonymous evaluation is allowed, whether more specific information such as uploading pictures and videos is advocated, whether the evaluation will be graded according to the user's credit, whether users can discuss a certain evaluation, and whether the objective facility level of the merchant is included to obtain the balance evaluation score of the evaluation. The evaluation method for the rationality evaluation of the scoring system can be: comprehensively score according to the dimensions of scoring, whether the scoring criteria are unified and easy to understand, whether the scoring will be graded according to the degree of detail (number of words, pictures), and whether the evaluation requires an explanation of the specific reasons for satisfaction or dissatisfaction to obtain the rationality evaluation score of the scoring system. The evaluation method for negative evaluation can be: comprehensively score according to the proportion of negative evaluations, whether the location has made improvements on negative evaluations, and whether the negative evaluations are extreme and significantly affect the experience to obtain the negative evaluation score. The evaluation method for the display evaluation of evaluations can be: score according to whether the display of evaluations is concise, whether it will be displayed according to the user's personalized collection and highlight the issues that users care about, whether it is objective and there is no concealment, and whether a summary or comprehensive score or trend analysis is provided, and finally obtain the display evaluation score of the evaluation.

[0090] In one embodiment, the advantage evaluation includes the evaluation of the fit between the advantage and the user preference, the evaluation of the importance and influence of the advantage, the evaluation of the accessibility and convenience of the advantage, and the evaluation of the user recognition and word-of-mouth of the advantage; in this embodiment, the scoring proportion of each part in the advantage evaluation can be preset. For example, for the evaluation of the fit between the advantage and the user preference, the evaluation of the importance and influence of the advantage, the evaluation of the accessibility and convenience of the advantage, and the evaluation of the user recognition and word-of-mouth of the advantage, for these four parts of evaluation, the scoring proportion of each part can be set to 25%. Then the advantage evaluation score is the sum of the scores of these four parts multiplied by 25% respectively, which is the final advantage evaluation score.

[0091] Among them, the evaluation method for the degree of fit between advantages and user preferences can be as follows: comprehensively score by judging whether the advantages match the user's core needs and preferences, and whether the advantages can be customized or adjusted according to the user's personalized preferences (such as dietary needs, landscape rooms, child-friendly facilities, etc.), so as to obtain the degree of fit score between the advantages and user preferences. The evaluation method for the importance and influence of advantages can be as follows: comprehensively score according to the core importance of the advantages (whether the advantages are the core highlights of the hotel, restaurant or scenic spot), the limited actual impact (whether the advantages really improve the user's overall experience), the persistence of the advantages (whether the advantages exist long-term, or are seasonal or occasional), and the uniqueness of the advantages (whether the advantages are unique to this hotel / restaurant / scenic spot). The evaluation method for the accessibility and convenience of advantages can be as follows: comprehensively score according to the availability of the advantages (whether users can conveniently enjoy this advantage) and whether there are quantity limitations for the advantages. The evaluation method for the user recognition and word-of-mouth of advantages can be as follows: comprehensively score according to whether the advantages evaluated by users are true and whether the cost performance meets the user's expectations.

[0092] In one embodiment, the disadvantage evaluation includes the evaluation of the non-conformity degree between the disadvantages and user needs, the evaluation of the severity and scope of influence of the disadvantages, the evaluation of the controllability and resolvability of the disadvantages, and the evaluation of the universality and transparency of the disadvantages. In this embodiment, the scoring ratio of each part in the disadvantage evaluation can be preset. For example, for the evaluation of the non-conformity degree between the disadvantages and user needs, the evaluation of the severity and scope of influence of the disadvantages, the evaluation of the controllability and resolvability of the disadvantages, and the evaluation of the universality and transparency of the disadvantages, for these four parts of evaluation, the scoring ratio of each part can be set to 25%. Then the disadvantage evaluation score is the sum of the scores of these four parts multiplied by 25% respectively, which is the final disadvantage evaluation.

[0093] Among them, the evaluation method for the non-conformity degree between the disadvantages and user needs can be as follows: comprehensively score according to whether the disadvantages directly affect the user's core needs, the severity and scope of influence of the disadvantages, whether the disadvantages affect the core influence of this location, whether the scope of influence of the disadvantages involves the current user, the frequency of occurrence of the disadvantages, and whether the disadvantages are sudden or persistent, so as to obtain the non-conformity degree score between the disadvantages and user needs. The evaluation method for the controllability and resolvability of the disadvantages can be as follows: comprehensively score according to whether the disadvantages are easily solved by the user's self-adjustment or the improvement of the location, whether the location has made improvements, whether the disadvantages are controllable, and whether the disadvantages are preventable, so as to obtain the controllability and resolvability score of the disadvantages. The evaluation method for the universality and transparency of the disadvantages can be as follows: comprehensively score according to whether the disadvantages are common in the same type of locations, whether the disadvantages are true, and whether users can conveniently learn about this disadvantage, so as to obtain the universality and transparency score of the disadvantages.

[0094] In one embodiment, a fourth weight value of each evaluation part among the location evaluation, the user preference evaluation, the cost performance evaluation, the network evaluation evaluation, the advantage evaluation, and the disadvantage evaluation can be set.

[0095] In the present application, the system can set initial weight values for each scoring part of the location evaluation, the user preference evaluation, the cost performance evaluation, the network evaluation evaluation, the advantage evaluation, and the disadvantage evaluation. And the user can adjust the weight values of each scoring part of the location evaluation, the user preference evaluation, the cost performance evaluation, the network evaluation evaluation, the advantage evaluation, and the disadvantage evaluation as needed to obtain the fourth weight value.

[0096] S203. Obtain the preference data of different users, perform denoising processing on the preference data, and convert the preference data into a vector form.

[0097] S204. Use the converted vector data as a data set to train the constructed user preference model, so that the user preference model outputs adjustment coefficients for each evaluation part.

[0098] In this embodiment, the preference data of the user can be converted into a vector form, and the noise data in the preference data can be cleared. The denoised data is used as a data set for training the user preference model. It should be noted that the user preference model is a deep learning model, and its output is the adjustment coefficients for each evaluation part.

[0099] S205. Input the preference information of the user into the trained user preference model, and output the first weight values of each evaluation part after adjustment.

[0100] S206. Calculate the final evaluation score of the user based at least on the first weight values of each evaluation part after adjustment and the scoring scores of each evaluation part.

[0101] In this embodiment, the adjustment coefficient can be used to adjust the weight coefficients of each evaluation part in the current evaluation process. For example, the initial weight values of the location evaluation, the user preference evaluation, the cost performance evaluation, the network evaluation evaluation, the advantage evaluation, and the disadvantage evaluation are set to 2:2:2:2:1:1. After inputting the preference data of the user into the user preference model, the obtained adjustment coefficient is 5:1:1:1:1:1. Then the final first weight value of each evaluation part is 7 / 22:3 / 22:3 / 22:3 / 22:2 / 22:2 / 22:2 / 22. The weight value of each evaluation part can be multiplied by the score of each evaluation part to calculate the final evaluation score of the user.

[0102] In one embodiment, step S206 may include: performing weighted calculation on the first weight values of each evaluation part and the scoring scores of each evaluation part to obtain the scores of each evaluation part.

[0103] Add up the scores of each evaluation part to obtain the user's final evaluation score.

[0104] Step S206 may further include: calculating a third weight value according to the adjusted first weight values of each evaluation part and the second weight values of each evaluation part set by the user; performing weighted calculation according to the third weight value and the scoring scores of each evaluation part to obtain the scores of each evaluation part; adding up the scores of each evaluation part to obtain the user's final evaluation score.

[0105] It should be noted that the user can also manually set the second weight value of each evaluation part according to their own preferences, then multiply the first weight value of each evaluation part by the second weight value of each evaluation part to obtain the third weight value of each evaluation part, and then multiply the third weight value of each evaluation part by the scoring score of each evaluation part to obtain the scores of each evaluation part; finally, add up the scores of each evaluation part to obtain the user's final evaluation score.

[0106] S207. Adjust the output planning result of the large model based on the evaluation score.

[0107] It should be noted that in a travel assistant model that can provide intelligent services for users, the travel assistant model can adjust the parameters in the travel assistant model according to the user's evaluation results, so as to provide a planning result that meets the user's needs.

[0108] The technical solution of the embodiment of the present invention calculates the scores of each scoring part based on the user information list, and inputs the user's preference information into the trained user preference model to output the adjusted first weight values of each evaluation part, and then calculates the final score of the user, thereby generating a highly personalized evaluation result; moreover, the present invention allows the user to customize the weight of each evaluation criterion in the overall score according to their own needs and preferences, thereby generating a highly personalized evaluation result and improving the practicality and pertinence of the result. In addition, the present invention can flexibly respond to changes in different scenarios and requirements, and can also be aimed at the same user, different scenarios or different plan changes under the same preference list. For example, the same user wants to formulate two plans, one is high-end travel and the other is economy travel. If it is a traditional method, only one score of the location can be seen, but after inputting their own preferences, the score differences brought by different user needs under the same location can be seen.

[0109] Embodiment III

[0110] Figure 3 It is a schematic structural diagram of a comprehensive evaluation device based on user preferences provided by Embodiment III of the present invention. As Figure 3 shown, the device includes:

[0111] An acquisition unit 301, configured to acquire a user's information list, where the information list at least includes the user's basic information, the user's favorite information, and the user's planning information;

[0112] A scoring unit 302, configured to score multiple evaluation parts of a travel destination according to the information list and objective data of the travel destination; the multiple evaluation parts at least include location, user preference, cost performance, online evaluation, advantages, and disadvantages;

[0113] A weight adjustment unit 303, configured to input the user's preference information into a trained user preference model, and output the first weight value of each adjusted evaluation part;

[0114] An evaluation unit 304, configured to calculate the user's final evaluation score based at least on the first weight value of each adjusted evaluation part and the scoring scores of each evaluation part;

[0115] A planning unit 305, configured to adjust the output planning result of the large model based on the evaluation score.

[0116] The comprehensive evaluation device based on user preference provided by the embodiments of the present invention can execute the comprehensive evaluation device based on user preference provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0117] Embodiment 4

[0118] Figure 4 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described herein and / or claimed.

[0119] As Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0120] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0121] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a resource scheduling method for message data processing.

[0122] In some embodiments, a resource scheduling method for message data processing can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the resource scheduling method for message data processing described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute a resource scheduling method for message data processing by any other suitable means (e.g., by means of firmware).

[0123] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0124] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0125] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0126] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. 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, voice input, or tactile input).

[0127] 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 to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0128] A computing system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The relationship between the client and the server is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0129] 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 the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0130] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. 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 principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A comprehensive evaluation method based on user preferences, characterized in that Including: Obtain a user's information list, where the information list at least includes the user's basic information, the user's collection information, and the user's planning information; Score multiple evaluation parts of a travel destination based on the information list and the objective data of the travel destination; the multiple evaluation parts at least include location, user preferences, cost performance, online reviews, advantages, and disadvantages; Input the user's preference information into the trained user preference model, and output the first weight value of each adjusted evaluation part; Calculate the user's final evaluation score based at least on the first weight value of each adjusted evaluation part and the scoring scores of each evaluation part; Adjust the output planning result of the large model based on the evaluation score.

2. The comprehensive evaluation method based on user preferences according to claim 1, characterized in that, The scoring of multiple evaluation parts of a travel destination based on the information list and the objective data of the travel destination includes: Divide the information list and the objective data of the travel destination according to location, user preferences, cost performance, online reviews, advantages, and disadvantages, and input them into the location score evaluation function, user preference evaluation function, cost performance evaluation function, online review evaluation function, advantage evaluation function, and disadvantage evaluation function respectively to score each evaluation part.

3. The comprehensive evaluation method based on user preferences according to claim 1, wherein Before the step of inputting the user's preference information into the trained user preference model and outputting the adjustment coefficient of each adjusted evaluation part, it further includes: Obtain the preference data of different users, perform denoising processing on the preference data, and convert the preference data into vector form; Use the converted vector data as a data set to train the constructed user preference model, so that the user preference model outputs the adjustment coefficient of each evaluation part.

4. The comprehensive evaluation method based on user preferences according to claim 1, wherein The calculation of the user's final evaluation score based at least on the first weight value of each adjusted evaluation part and the scoring scores of each evaluation part includes: Perform weighted calculation on the first weight value of each evaluation part and the scoring scores of each evaluation part to obtain the score of each evaluation part; Add up the scores of each evaluation part to obtain the user's final evaluation score.

5. The comprehensive evaluation method based on user preferences according to claim 1, characterized in that, The calculation of the user's final evaluation score based at least on the weight value of each adjusted evaluation part and the scoring scores of each evaluation part includes: Calculate the third weight value according to the first weight value of each adjusted evaluation part and the second weight value of each evaluation part set by the user; Perform weighted calculation according to the third weight value and the scoring scores of each evaluation part to obtain the score of each evaluation part; Add up the scores of each evaluation part to obtain the user's final evaluation score.

6. The comprehensive evaluation method based on user preferences according to claim 1, wherein, Location evaluation includes transportation convenience evaluation, surrounding environment evaluation, commercial and living facilities evaluation, weather and climate evaluation, and geographical location and regional evaluation; User preference evaluation includes user collection evaluation, historical preference evaluation, travel purpose matching, budget and price preference evaluation, geographical location preference evaluation, and entertainment preference evaluation; Cost performance evaluation includes price and service matching degree evaluation, facilities and service evaluation, additional service or discount evaluation, competitor comparison, time period and season price evaluation, and surrounding market and living cost evaluation; The network evaluation assessment includes the timeliness assessment of evaluations, the balance assessment of evaluations, the rationality assessment of the scoring system, the negative evaluation assessment, and the display assessment of evaluations; The advantage assessment includes the assessment of the fit between advantages and user preferences, the assessment of the importance and influence of advantages, the assessment of the accessibility and convenience of advantages, and the assessment of user recognition and word-of-mouth of advantages; The disadvantage assessment includes the assessment of the non-conformity between disadvantages and user needs, the assessment of the severity and scope of influence of disadvantages, the assessment of the controllability and resolvability of disadvantages, and the assessment of the universality and transparency of disadvantages.

7. The comprehensive evaluation method based on user preferences according to claim 6, characterized in that, It also includes: The fourth weight values of each assessment part in the location assessment, the user preference assessment, the cost performance assessment, the network evaluation assessment, the advantage assessment, and the disadvantage assessment are respectively set.

8. An integrated evaluation device based on user preferences, characterized in that It includes: An acquisition unit for acquiring a user information list, where the information list at least includes the user's basic information, the user's favorite information, and the user's planning information; A scoring unit for scoring multiple assessment parts of a travel location according to the information list and the objective data of the travel location; the multiple assessment parts at least include location, user preference, cost performance, network evaluation, advantages, and disadvantages; A weight adjustment unit for inputting the user's preference information into a trained user preference model and outputting the first weight value of each adjusted assessment part; An evaluation unit for calculating the user's final evaluation score at least based on the first weight value of each adjusted assessment part and the scoring scores of each assessment part; A planning unit for adjusting the output planning result of the large model based on the evaluation score.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the comprehensive evaluation method based on user preferences according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to implement the comprehensive evaluation method based on user preferences according to any one of claims 1-7 when executed.

Images